© 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. 5348
    Prev
    Next
    INDEX
    Explanations

    for informational purposes only

    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
    ें
    0.71
    a
    0.68
    े
    0.63
    as
    0.63
    quela
    0.62
    ומי
    0.61
     оплаты
    0.56
    اء
    0.55
    en
    0.53
    quele
    0.53
    POSITIVE LOGITS
     NotFound
    0.60
    儡
    0.57
    鹉
    0.51
    والفقار
    0.51
     suburb
    0.50
    msgs
    0.50
    ม่า
    0.50
    ید
    0.49
     tris
    0.49
    DURATION
    0.48
    Activations Density 0.036%

    No Known Activations