© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78631
    Prev
    Next
    INDEX
    Explanations

    hippie movement, vibe, chick / Douala, Douro, Douyin

    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_0_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
     in
    1.66
    s
    1.45
    t
    1.40
    ьте
    1.21
     to
    1.17
    sı
    1.16
    ی
    1.16
    с
    1.14
    да
    1.10
     trombone
    1.10
    POSITIVE LOGITS
    ла
    2.09
    า
    1.53
    使用
    1.43
    on
    1.38
    ה
    1.38
    of
    1.38
    '
    1.32
    ת
    1.30
    高
    1.30
    .
    1.28
    Activations Density 0.000%

    No Known Activations