© 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. 10205
    Prev
    Next
    INDEX
    Explanations

    code and code-related configuration

    oai_token-act-pair · gemini-2.0-flash

    Code/Programming

    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
    AddHtmlAttribute
    -0.65
    EditorBrowsable
    -0.52
    UnknownFields
    -0.52
    InsertCommand
    -0.51
     defaultstate
    -0.51
    *);
    -0.50
    Demografie
    -0.50
     LoggerFactory
    -0.49
     HttpHeaders
    -0.48
    igate
    -0.47
    POSITIVE LOGITS
    Vern
    0.63
    mobileqq
    0.60
    afficheront
    0.57
     Vern
    0.57
     soutenu
    0.55
     mû
    0.54
    usepackage
    0.51
    KEYCODE
    0.51
    例文帳に追加
    0.51
     VERN
    0.51
    Activations Density 1.398%

    No Known Activations