© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 86019
    Prev
    Next
    INDEX
    Explanations

    refuse to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    Ө
    0.77
     ی
    0.76
    Ә
    0.76
     زمین
    0.76
    ัด
    0.75
    도
    0.72
    Θ
    0.67
     سعید
    0.66
    Як
    0.66
    Ä
    0.65
    POSITIVE LOGITS
    c
    1.15
    <0x80>
    1.00
    t
    0.94
    d
    0.81
    b
    0.78
    cón
    0.76
    ing
    0.73
    га
    0.68
     diseñ
    0.66
    dle
    0.66
    Activations Density 0.001%

    No Known Activations