© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131715
    Prev
    Next
    INDEX
    Explanations

    ghoul, wight, draugr

    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
    s
    2.09
    0
    1.59
    t
    1.55
    test
    1.24
    f
    1.23
    1
    1.22
    c
    1.21
    a
    1.20
    tan
    1.19
    in
    1.18
    POSITIVE LOGITS
    ב
    1.59
    ר
    1.54
    та
    1.30
    र
    1.26
     clínicas
    1.24
     políticas
    1.20
    ;
    1.20
    ס
    1.19
    ર
    1.17
     pessoal
    1.14
    Activations Density 0.000%

    No Known Activations