© 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. 161755
    Prev
    Next
    INDEX
    Explanations

    encyclopedia and encyclopedias

    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
    -
    1.49
    습니다
    1.47
    ции
    1.25
    ación
    1.20
    ۵
    1.18
    (
    1.15
    是怎么
    1.13
     be
    1.13
    ४
    1.10
    ão
    1.08
    POSITIVE LOGITS
    ุ
    1.80
    на
    1.77
    the
    1.70
    ان
    1.68
    ری
    1.68
    ال
    1.63
    R
    1.61
    ні
    1.56
    t
    1.49
    د
    1.46
    Activations Density 0.000%

    No Known Activations