© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 14432
    Prev
    Next
    INDEX
    Explanations

    what to offer

    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_15_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
    iav
    0.37
    *,
    0.35
    ihara
    0.35
    inaan
    0.34
    arashtra
    0.34
    oro
    0.34
    m
    0.33
    avy
    0.33
    **,
    0.32
    uable
    0.32
    POSITIVE LOGITS
    フランス
    0.29
    लेकिन
    0.28
    員
    0.28
    циона
    0.27
     diocese
    0.27
     ഒരിക്ക
    0.26
     kiló
    0.26
    在
    0.26
     लेकिन
    0.25
    ნი
    0.25
    Activations Density 0.036%

    No Known Activations