© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1734
    Prev
    Next
    INDEX
    Explanations

    code artifacts like parameters, variables, class/object attributes, and objects being instantiated

    oai_token-act-pair · gemini-2.0-flash

    code identifiers or functions

    np_token-act-pair-logits · gpt-4o-mini

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     doubtnut
    -0.61
     Monfieur
    -0.57
    modelBuilder
    -0.57
     Ephraim
    -0.56
     itſelf
    -0.55
     Suf
    -0.54
     Brutus
    -0.53
    seamnă
    -0.52
     Senat
    -0.52
     Bemer
    -0.52
    POSITIVE LOGITS
    fjspx
    0.64
     Signalez
    0.63
    İstinadlar
    0.58
    Personendaten
    0.57
    GraphicsUnit
    0.55
    évaluateur
    0.54
    ंदीखरीदारी
    0.53
    WithIOException
    0.53
     @"/
    0.52
    Pyx
    0.52
    Activations Density 0.724%

    No Known Activations