© 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. 5329
    Prev
    Next
    INDEX
    Explanations

    mentions of inventions and dates.

    oai_token-act-pair · gemini-2.0-flash

    Trade

    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
    Xna
    -0.75
    号
    -0.58
    Label
    -0.57
    LLocation
    -0.57
     autorytatywna
    -0.57
    Comté
    -0.56
    materi
    -0.56
     Title
    -0.56
    atific
    -0.56
     label
    -0.55
    POSITIVE LOGITS
     trade
    0.63
    expandindo
    0.59
    trade
    0.58
    AndEndTag
    0.57
    MigrationBuilder
    0.56
     registered
    0.48
    enterOuterAlt
    0.48
     kaarangay
    0.47
     Trade
    0.46
    Trade
    0.46
    Activations Density 3.216%

    No Known Activations