© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3830
    Prev
    Next
    INDEX
    Explanations

    words related to capability and blame

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     étoit
    -1.12
     auroit
    -1.09
     avoient
    -1.05
     enfans
    -1.04
     feroit
    -1.02
     مشين
    -0.99
     ainfi
    -0.96
     Theſe
    -0.96
     Monfieur
    -0.96
     autorytatywna
    -0.92
    POSITIVE LOGITS
     
    0.75
    -
    0.73
     and
    0.72
    ,
    0.70
     R
    0.69
     $
    0.69
     (
    0.67
     A
    0.65
     or
    0.64
     -
    0.64
    Activations Density 0.845%

    No Known Activations