© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103663
    Prev
    Next
    INDEX
    Explanations

    Swedish/German/Japanese word endings

    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_1_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
    ка
    1.02
    ați
    1.00
    ه
    0.93
    .
    0.91
    ан
    0.90
    лли
    0.89
    ك
    0.89
    a
    0.87
    ент
    0.85
     Ủy
    0.85
    POSITIVE LOGITS
     an
    1.57
     with
    1.44
     at
    1.39
     it
    1.33
     of
    1.30
     on
    1.27
     that
    1.20
     to
    1.19
     from
    1.13
     be
    1.11
    Activations Density 0.000%

    No Known Activations