© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156485
    Prev
    Next
    INDEX
    Explanations

    improvise

    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_2_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
    μα
    1.16
    ov
    1.09
    CH
    1.04
    (
    1.02
    SE
    0.98
    ﺍ
    0.95
    தால்
    0.95
     ampli
    0.95
    _
    0.95
    J
    0.95
    POSITIVE LOGITS
     is
    1.13
    д
    1.10
    is
    1.07
    מ
    1.07
    ני
    1.06
    مي
    1.05
    ية
    1.04
    د
    1.01
    ки
    0.99
    ם
    0.98
    Activations Density 0.000%

    No Known Activations