© 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. 14075
    Prev
    Next
    INDEX
    Explanations

    descriptions of car features and technology

    oai_token-act-pair · gemini-2.0-flash

    vehicle driver assistance features

    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
    yaitu
    -0.66
    Specifiche
    -0.65
     Shet
    -0.58
    Esperamos
    -0.58
    ὺς
    -0.58
    .");
    -0.57
    )");
    -0.57
    Tradu
    -0.57
    ."));
    -0.57
    ῖς
    -0.56
    POSITIVE LOGITS
     arşivlendi
    0.56
    XmlAccessorType
    0.52
    aarrggbb
    0.51
    WriteBarrier
    0.50
     يتيمه
    0.50
     ITIS
    0.49
    Tikang
    0.49
    inerea
    0.49
    zarchiwizowane
    0.48
     الحره
    0.48
    Activations Density 1.451%

    No Known Activations