© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5793
    Prev
    Next
    INDEX
    Explanations

    technical descriptions of physical processes

    oai_token-act-pair · gemini-2.0-flash

    value

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     moindre
    -0.54
     typelib
    -0.51
    UIControlState
    -0.50
     καν
    -0.48
    gnose
    -0.44
     extranjera
    -0.44
     couvrir
    -0.44
    Tracked
    -0.44
     Dingen
    -0.44
    pele
    -0.44
    POSITIVE LOGITS
     value
    1.09
     values
    0.93
    value
    0.91
     valeur
    0.79
     VALUE
    0.77
    値
    0.74
     Value
    0.71
     giá
    0.71
     valeurs
    0.70
    Value
    0.69
    Activations Density 11.213%

    No Known Activations