© 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. 4025
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, especially annotations, brackets, and keywords like "returns", "true," "if", "bool", "var", "will", and "value".

    oai_token-act-pair · gemini-2.0-flash

    code documentation

    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
    .
    -0.76
    !
    -0.74
    [
    -0.74
    ,
    -0.73
    :
    -0.71
    ;
    -0.71
    (
    -0.68
    *
    -0.67
    |
    -0.66
    2
    -0.65
    POSITIVE LOGITS
     CreateTagHelper
    1.47
     EconPapers
    1.30
     OFDb
    1.12
     saites
    1.09
    ScopeManager
    1.09
    __":
    1.08
    "])
    1.08
    Билгалдахарш
    1.06
     дописавши
    1.02
     ExecuteAsync
    1.02
    Activations Density 0.539%

    No Known Activations