© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88085
    Prev
    Next
    INDEX
    Explanations

    first pass or first decisions

    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
     are
    0.72
     ativo
    0.71
     be
    0.71
    ﻒ
    0.71
    FileOutputStream
    0.71
     și
    0.70
    সময়
    0.70
     ventral
    0.70
    Arquivo
    0.68
    LENGTH
    0.68
    POSITIVE LOGITS
    -
    0.97
    ק
    0.77
    '
    0.75
    ت
    0.65
    ת
    0.61
    ون
    0.61
    то
    0.60
    ek
    0.57
     которого
    0.56
    ird
    0.55
    Activations Density 0.015%

    No Known Activations