© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 210793
    Prev
    Next
    INDEX
    Explanations

    question marks followed by solve

    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_5_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
    ل
    1.47
    л
    1.37
    ul
    1.30
    س
    1.23
    ే
    1.22
    ض
    1.21
    اء
    1.16
    ת
    1.15
    ή
    1.14
    ز
    1.13
    POSITIVE LOGITS
    P
    1.27
    K
    1.22
    C
    1.15
    M
    1.14
    ’
    1.09
    G
    1.03
     что
    1.02
     aŭ
    1.01
     に
    1.00
     למ
    1.00
    Activations Density 0.002%

    No Known Activations