© 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. 107790
    Prev
    Next
    INDEX
    Explanations

    *n' followed by '

    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
    स
    1.25
    ש
    1.24
    ס
    1.23
    لي
    1.22
    מ
    1.19
    한
    1.17
    не
    1.15
    ă
    1.15
    ü
    1.13
    ד
    1.09
    POSITIVE LOGITS
    kę
    0.95
    gning
    0.94
    0
    0.93
    gger
    0.92
    ća
    0.91
    ০০০
    0.91
    kette
    0.91
     غیر
    0.88
    kta
    0.88
    ியும்
    0.88
    Activations Density 0.000%

    No Known Activations