© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33517
    Prev
    Next
    INDEX
    Explanations

    взаимо/interaction

    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_3_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
    ش
    0.72
     an
    0.71
    H
    0.70
    ag
    0.68
    exercice
    0.68
    TimeTo
    0.68
     jugar
    0.66
    يت
    0.66
    "};
    0.66
    unov
    0.64
    POSITIVE LOGITS
    u
    0.84
    ία
    0.72
    er
    0.71
    彼此
    0.71
    s
    0.67
     tangy
    0.65
     लड़की
    0.65
    y
    0.64
    z
    0.64
    in
    0.63
    Activations Density 0.002%

    No Known Activations