© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230505
    Prev
    Next
    INDEX
    Explanations

    Strepsils

    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_6_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
    OpportunitiesBy
    0.99
     extraño
    0.95
     ℝ
    0.94
     ני
    0.92
     imprend
    0.91
     aumento
    0.90
     estrem
    0.90
     injure
    0.87
     operador
    0.87
     ジェ
    0.86
    POSITIVE LOGITS
    it
    1.53
    س
    1.48
    on
    1.45
    are
    1.32
    К
    1.30
    L
    1.29
    Т
    1.25
    as
    1.17
    。
    1.13
    N
    1.07
    Activations Density 0.000%

    No Known Activations