© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8911
    Prev
    Next
    INDEX
    Explanations

    the word "team" and also analyze team performance in terms of player statistics

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Kappa
    -0.47
     radic
    -0.44
    nocache
    -0.43
     Against
    -0.43
    واسطة
    -0.43
    স্
    -0.42
     adoptar
    -0.42
    yong
    -0.42
     refuser
    -0.42
     novel
    -0.41
    POSITIVE LOGITS
    '])){
    0.75
    Personendaten
    0.75
    +#+#
    0.75
    abestanden
    0.71
    zzleHttp
    0.68
    extAlignment
    0.68
     Audiodateien
    0.66
    "},
    0.63
     Мексичка
    0.63
     kaarangay
    0.63
    Activations Density 2.660%

    No Known Activations