© 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. 7232
    Prev
    Next
    INDEX
    Explanations

    phrases and names related to large philanthropic organizations and their work in education.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and specific identifiers

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

    organizations and projects

    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
    åd
    -0.46
     transform
    -0.43
    lawesi
    -0.41
    DispatchToProps
    -0.40
     al
    -0.40
    labelledby
    -0.40
    prev
    -0.39
    יפה
    -0.38
     rendez
    -0.38
    transform
    -0.37
    POSITIVE LOGITS
    tvguidetime
    0.90
     виправивши
    0.77
    SequentialGroup
    0.75
    StructEnd
    0.74
     BorderRadius
    0.73
    PerformLayout
    0.73
    matchCondition
    0.73
    
    0.72
     OFDb
    0.71
     betweenstory
    0.71
    Activations Density 0.860%

    No Known Activations