© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10266
    Prev
    Next
    INDEX
    Explanations

    fragments of instruction-like language, as in "if you..., then..." or "you have to..."

    oai_token-act-pair · gemini-2.0-flash

    Online browsing actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Obrázky
    -0.83
    MigrationBuilder
    -0.81
    клопе
    -0.75
    AddTagHelper
    -0.70
    Looking
    -0.67
     looking
    -0.64
     looked
    -0.62
    LOOKING
    -0.61
     étoit
    -0.61
     مُعرِّف
    -0.60
    POSITIVE LOGITS
     per
    0.71
    TintMode
    0.64
    TheReal
    0.57
     sit
    0.50
     plot
    0.50
    ourne
    0.49
     Per
    0.49
    ukunft
    0.49
    TabIndex
    0.49
     Act
    0.48
    Activations Density 4.117%

    No Known Activations