© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231485
    Prev
    Next
    INDEX
    Explanations

    attribute to

    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_6_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
    夫
    1.08
    OW
    1.03
     by
    1.02
    IT
    0.97
    3
    0.96
    עם
    0.94
    ની
    0.90
    ET
    0.89
    ADH
    0.88
    의
    0.87
    POSITIVE LOGITS
    to
    0.88
    ti
    0.88
    ado
    0.87
    ulated
    0.87
    baiki
    0.87
    andez
    0.86
     To
    0.80
     to
    0.79
     In
    0.77
    tede
    0.75
    Activations Density 0.001%

    No Known Activations