© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10519
    Prev
    Next
    INDEX
    Explanations

    pronouns, especially 'it', 'them', 'us', 'him', or 'her' close to the verb make.

    oai_token-act-pair · gemini-2.0-flash

    conditional statements and eligibility terms

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

    debates and discussions

    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
     be
    -0.91
     Soyez
    -0.79
     is
    -0.73
     быть
    -0.73
     být
    -0.70
     бути
    -0.69
     essere
    -0.68
     être
    -0.66
     being
    -0.63
     soient
    -0.63
    POSITIVE LOGITS
    ]--;
    0.81
     eligible
    0.75
     ExecuteAsync
    0.68
    styleable
    0.66
     ineligible
    0.66
    TemporalType
    0.65
    CppMethod
    0.64
    gonic
    0.64
     wikipagina
    0.64
    eligible
    0.63
    Activations Density 2.335%

    No Known Activations