© 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. 156535
    Prev
    Next
    INDEX
    Explanations

    imprisonment as consequence

    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
    ור
    1.74
    า
    1.74
     It
    1.63
     In
    1.55
    س
    1.46
    ס
    1.43
     I
    1.38
    y
    1.38
     A
    1.38
     The
    1.37
    POSITIVE LOGITS
    ètre
    1.45
    <0x80>
    1.41
    étaire
    1.32
     лише
    1.32
     ника
    1.27
    ４
    1.20
    ５
    1.18
    hiddenMap
    1.16
    obaan
    1.16
    ида
    1.16
    Activations Density 0.001%

    No Known Activations