© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5195
    Prev
    Next
    INDEX
    Explanations

    HTML code related to input types in forms

    oai_token-act-pair · gemini-2.0-flash

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    RTDA
    -0.62
    ivas
    -0.44
    []{"
    -0.43
     виправивши
    -0.43
     étr
    -0.43
    tiéndose
    -0.43
    netbeans
    -0.43
    subtype
    -0.43
     [],
    -0.43
     '',
    -0.43
    POSITIVE LOGITS
    GraphicsUnit
    0.68
    ymce
    0.65
    enumi
    0.65
    Viited
    0.57
     jScrollPane
    0.57
     Gleaner
    0.55
    Izvori
    0.54
    VIAF
    0.54
    PhysRevD
    0.52
    Eksterne
    0.52
    Activations Density 3.591%

    No Known Activations