© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5595
    Prev
    Next
    INDEX
    Explanations

    at the time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝙡
    1.93
    д
    1.86
    mapper
    1.84
    и
    1.77
     bisschen
    1.68
    ാൻ
    1.65
    𝙚
    1.62
    كمال
    1.61
    häng
    1.60
    ве
    1.60
    POSITIVE LOGITS
    员
    1.89
    ant
    1.85
    мся
    1.80
    tien
    1.79
    ously
    1.74
    t
    1.74
    ophenyl
    1.74
    <0xCA>
    1.69
    fname
    1.66
     листопада
    1.65
    Activations Density 0.002%

    No Known Activations