© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78621
    Prev
    Next
    INDEX
    Explanations

    probability fractions

    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_29_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
     scheme
    0.33
    Coupon
    0.32
     Беларусі
    0.31
    blich
    0.30
    謀
    0.29
    Modulo
    0.29
    ipped
    0.29
    Subset
    0.29
    arantad
    0.29
    ndarray
    0.29
    POSITIVE LOGITS
     counterbalance
    0.34
     Avoid
    0.33
     Ur
    0.32
     regenerative
    0.32
     avoid
    0.31
     negotiator
    0.31
    ={$
    0.31
     مشکلات
    0.31
     pracovní
    0.30
     vow
    0.30
    Activations Density 0.012%

    No Known Activations