© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 121702
    Prev
    Next
    INDEX
    Explanations

    immigration

    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
    ва
    0.75
    ная
    0.72
    하다
    0.69
    시
    0.69
    ді
    0.67
    다
    0.64
    ца
    0.64
    اه
    0.63
    ные
    0.61
    ால்
    0.60
    POSITIVE LOGITS
    ک
    0.63
    א
    0.61
    ק
    0.60
    ي
    0.59
    ort
    0.59
    Е
    0.58
     ש
    0.57
    হ
    0.56
    ท
    0.56
    <0x0D>
    0.55
    Activations Density 0.000%

    No Known Activations