© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 460
    Prev
    Next
    INDEX
    Explanations

    scientific and academic text

    oai_token-act-pair · gemini-2.0-flash

    Physics understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    tagHelperRunner
    -0.43
     선
    -0.42
    jud
    -0.41
     Funeral
    -0.40
    zenz
    -0.39
    ^{-
    -0.39
    พล
    -0.39
    ed
    -0.38
     Y
    -0.38
     nach
    -0.38
    POSITIVE LOGITS
    ^(@)
    0.84
    جغرافيا
    0.83
     iſt
    0.83
     myſelf
    0.83
     Efq
    0.81
    حياته
    0.78
    Tikang
    0.77
    ſelf
    0.76
     يتيمه
    0.74
     الرياضيه
    0.74
    Activations Density 3.479%

    No Known Activations