© 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. 5207
    Prev
    Next
    INDEX
    Explanations

    data

    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
    ्य
    2.59
    𝓌
    2.58
    COOH
    2.38
    mamm
    2.37
    ве
    2.31
    ০১
    2.27
    ার
    2.27
     zadr
    2.25
     expr
    2.24
     ina
    2.19
    POSITIVE LOGITS
    ي
    2.51
    ouille
    2.46
    amiento
    2.31
    聵
    2.28
    іл
    2.25
     croire
    2.23
     النفس
    2.18
    ิ่ง
    2.17
     postoje
    2.15
     successive
    2.15
    Activations Density 0.000%

    No Known Activations