© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46426
    Prev
    Next
    INDEX
    Explanations

    lengthy prison

    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_10_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
    л
    1.10
    м
    1.03
    ب
    0.99
    م
    0.95
    д
    0.95
    ر
    0.92
    न
    0.85
    מ
    0.83
    й
    0.80
    গ
    0.79
    POSITIVE LOGITS
     fraud
    0.77
     chees
    0.70
    ollow
    0.67
    يد
    0.66
     butcher
    0.66
    يتها
    0.66
    ua
    0.63
    ти
    0.63
    وي
    0.63
     discouraging
    0.63
    Activations Density 0.007%

    No Known Activations