© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10362
    Prev
    Next
    INDEX
    Explanations

    tokens which often appear in Java code.

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
    AddTagHelper
    -0.86
    NameInMap
    -0.73
    __":
    -0.73
    Weblinks
    -0.69
    itness
    -0.69
    phazard
    -0.69
    roxene
    -0.69
    liminary
    -0.68
    pended
    -0.67
    niczy
    -0.66
    POSITIVE LOGITS
     ordinaria
    0.47
     dessutom
    0.45
     dámské
    0.44
     perpétu
    0.44
     umane
    0.43
     páns
    0.43
     mengikut
    0.42
     mauvaises
    0.42
     noastră
    0.42
     marchés
    0.42
    Activations Density 0.423%

    No Known Activations