© 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. 58161
    Prev
    Next
    INDEX
    Explanations

    DJ

    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
    ن
    1.45
    ي
    1.35
    د
    1.13
    ري
    1.06
    in
    1.04
     밝혔
    1.01
    وين
    0.99
    s
    0.98
    innt
    0.97
    hlas
    0.96
    POSITIVE LOGITS
     as
    1.64
    '
    1.46
    ’
    1.22
     \
    1.13
     for
    1.05
    ‘
    1.02
    로는
    0.98
    -
    0.98
    ка
    0.96
    im
    0.96
    Activations Density 0.000%

    No Known Activations