© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108286
    Prev
    Next
    INDEX
    Explanations

    daily basis

    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
    :
    1.02
     hogy
    0.96
     dotycz
    0.88
     ສ
    0.86
     that
    0.83
     الوطني
    0.77
     deportivas
    0.77
     muut
    0.75
     rattles
    0.75
    AY
    0.73
    POSITIVE LOGITS
    ش
    1.48
    то
    1.39
    ש
    1.37
    л
    1.29
    ار
    1.23
    ш
    1.23
    al
    1.20
    на
    1.20
    ם
    1.17
    ע
    1.16
    Activations Density 0.000%

    No Known Activations