© 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. 10102
    Prev
    Next
    INDEX
    Explanations

    terms that are related to weight

    oai_token-act-pair · gemini-2.0-flash

    weight

    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
     vectorielles
    -0.60
     دیکھیے
    -0.56
     egentlig
    -0.54
    utsches
    -0.53
     nourrir
    -0.53
     financières
    -0.52
    chtige
    -0.52
    мені
    -0.52
     λογ
    -0.52
    الحياه
    -0.51
    POSITIVE LOGITS
    RetentionPolicy
    0.63
    Tembelea
    0.60
    MigrationBuilder
    0.57
    UnknownFieldSet
    0.54
     Himo
    0.51
    InitVars
    0.50
    IVEREF
    0.50
    UnsafeEnabled
    0.49
     OFDb
    0.49
    GIVEREF
    0.48
    Activations Density 2.138%

    No Known Activations