© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14487
    Prev
    Next
    INDEX
    Explanations

    computer code keywords and names

    oai_token-act-pair · gemini-2.0-flash

    Code-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     And
    -0.97
     In
    -0.88
     We
    -0.87
     It
    -0.83
     The
    -0.80
     But
    -0.74
     To
    -0.69
     They
    -0.67
     This
    -0.66
     Its
    -0.66
    POSITIVE LOGITS
    PERATURE
    0.57
    WRENCE
    0.53
     film
    0.53
     الحره
    0.52
    webElementXpaths
    0.51
    FLICT
    0.51
    instancetype
    0.51
    OrFail
    0.51
     key
    0.50
    {~
    0.50
    Activations Density 9.000%

    No Known Activations