© 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. 734
    Prev
    Next
    INDEX
    Explanations

    names that begin with one or two capital letters followed by lowercase letters

    oai_token-act-pair · gemini-2.0-flash

    names and code

    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
     Мексичка
    -0.93
    migrationBuilder
    -0.91
    NameInMap
    -0.85
    ScopeManager
    -0.85
    Билгалдахарш
    -0.82
    principalTable
    -0.79
    CppMethod
    -0.75
     @}
    -0.75
    interopRequire
    -0.73
    kháu
    -0.73
    POSITIVE LOGITS
     humaines
    0.47
     humanas
    0.37
     Bedien
    0.36
     Hickey
    0.34
    azu
    0.34
     russes
    0.34
     humaine
    0.34
    anu
    0.33
     noires
    0.33
    aan
    0.32
    Activations Density 1.254%

    No Known Activations