© 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. 143240
    Prev
    Next
    INDEX
    Explanations

    slip condition or mat

    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
    ية
    1.68
    자
    1.65
    ский
    1.35
    सी
    1.29
    簹
    1.25
    ون
    1.24
    ي
    1.24
    ла
    1.23
     botched
    1.23
    사
    1.23
    POSITIVE LOGITS
    ↵↵
    1.95
    en
    1.46
    F
    1.36
    E
    1.31
    O
    1.30
    A
    1.29
    K
    1.29
    That
    1.27
    R
    1.23
     î
    1.22
    Activations Density 0.000%

    No Known Activations