© 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. 39792
    Prev
    Next
    INDEX
    Explanations

    arguments for

    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
    .
    0.71
    อิน
    0.71
     reconoc
    0.66
    itati
    0.66
    ibus
    0.65
     protéger
    0.65
     volition
    0.64
    houses
    0.64
     appré
    0.64
    หน้า
    0.63
    POSITIVE LOGITS
    ی
    0.89
     Arguments
    0.84
     Argument
    0.82
    Argument
    0.82
    ת
    0.81
    一
    0.76
    ı
    0.76
    argument
    0.75
    Arguments
    0.75
     argument
    0.75
    Activations Density 0.051%

    No Known Activations