© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16334
    Prev
    Next
    INDEX
    Explanations

    code-related words like "generated," "async," "code," "file," "http," and "response"

    oai_token-act-pair · gemini-2.0-flash

    Code generation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
      
    -0.46
    enal
    -0.46
    DICTION
    -0.44
    ATUS
    -0.41
    ELAND
    -0.40
    statistics
    -0.39
    MOUS
    -0.39
    pros
    -0.39
    maining
    -0.39
    ASTIC
    -0.38
    POSITIVE LOGITS
     doubtnut
    0.75
    uxxxx
    0.75
     ―――――
    0.74
    RectangleBorder
    0.71
     Winaray
    0.70
     ་་
    0.69
     Reſ
    0.69
     iſt
    0.68
    Personensuche
    0.66
    WithIOException
    0.66
    Activations Density 5.582%

    No Known Activations