© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14932
    Prev
    Next
    INDEX
    Explanations

    a variety of words related to diverse specific topics like law, education, computer bug reports, historical conflicts, and medicine.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and code-related phrases

    np_token-act-pair-logits · gpt-4o-mini

    news reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     situation
    -0.69
    situation
    -0.60
     system
    -0.60
     community
    -0.57
     ecosystem
    -0.53
     the
    -0.53
     dilemma
    -0.52
     population
    -0.52
    the
    -0.51
    gway
    -0.51
    POSITIVE LOGITS
    下载附件
    0.84
    NameInMap
    0.77
     CanadaChoose
    0.66
    imetry
    0.64
    IntoConstraints
    0.61
    ArgsConstructor
    0.59
    rungsseite
    0.57
    PerformLayout
    0.57
     initComponents
    0.57
    
    0.57
    Activations Density 5.635%

    No Known Activations