© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227569
    Prev
    Next
    INDEX
    Explanations

    bring back to

    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_6_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
    ного
    0.88
     míst
    0.87
    िक
    0.86
    AIN
    0.80
     evita
    0.80
    ﻱ
    0.79
    ARE
    0.79
    ﺭ
    0.77
     senc
    0.77
     وګټ
    0.76
    POSITIVE LOGITS
    ال
    1.39
    ح
    1.19
    in
    1.09
    د
    1.06
    I
    1.05
     the
    1.01
     is
    1.01
    ت
    0.99
    K
    0.98
    O
    0.96
    Activations Density 0.000%

    No Known Activations