© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1346
    Prev
    Next
    INDEX
    Explanations

    locations, especially US locations in the form "XX ##..."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    UnsafeEnabled
    -0.44
     control
    -0.43
    Enders
    -0.41
    addPreferredGap
    -0.41
     skru
    -0.40
     Go
    -0.39
     
    -0.38
    外部リンク
    -0.37
    mks
    -0.37
    tyard
    -0.37
    POSITIVE LOGITS
     ModelExpression
    0.83
    uxxxx
    0.77
    yntaxException
    0.69
     recens
    0.68
    ########.
    0.68
    ArgumentParser
    0.67
     Correspond
    0.66
     Unauthorized
    0.66
    TintMode
    0.65
     disponibilités
    0.64
    Activations Density 0.292%

    No Known Activations