© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 14128
    Prev
    Next
    INDEX
    Explanations

    options or alternatives

    oai_token-act-pair · gemini-2.0-flash

    choices or alternatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     disponibilités
    -0.66
    RegressionTest
    -0.65
     Normdatei
    -0.62
    HideFlags
    -0.60
    DockStyle
    -0.60
    حياته
    -0.60
    )");
    -0.59
    "]);
    -0.57
    endmodule
    -0.54
    )):
    -0.54
    POSITIVE LOGITS
     or
    1.03
     hoặc
    0.94
     atau
    0.90
    Или
    0.87
     Alternatively
    0.87
    Alternatively
    0.86
     either
    0.85
     eller
    0.83
     либо
    0.83
     entweder
    0.81
    Activations Density 1.033%

    No Known Activations