© 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. 58386
    Prev
    Next
    INDEX
    Explanations

    per

    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
    ی
    1.29
    nite
    1.15
    nya
    1.10
    มัน
    1.08
    taining
    1.05
    ként
    1.03
    یان
    1.03
    ία
    1.02
    ków
    1.02
    ่
    1.02
    POSITIVE LOGITS
    in
    1.77
    et
    1.39
    K
    1.33
    ot
    1.24
    os
    1.16
    m
    1.12
    ية
    1.09
    y
    1.09
    e
    1.08
    b
    1.08
    Activations Density 0.000%

    No Known Activations