© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13410
    Prev
    Next
    INDEX
    Explanations

    future directions

    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_13_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
    s
    0.34
    P
    0.34
    st
    0.32
    b
    0.32
    B
    0.31
    d
    0.30
    w
    0.30
    del
    0.29
    T
    0.29
    L
    0.28
    POSITIVE LOGITS
     करिकुलम
    0.34
     કારણ
    0.32
     seca
    0.30
    `}
    0.29
    ಣೆ
    0.29
     cenderung
    0.29
    வுக்கு
    0.28
     mascota
    0.28
     remem
    0.28
    வோ
    0.28
    Activations Density 0.003%

    No Known Activations