© 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. 33278
    Prev
    Next
    INDEX
    Explanations

    future generations or years

    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
    Negative Logits
     can
    0.80
    can
    0.66
    ة
    0.66
     a
    0.64
     i
    0.64
     impenetrable
    0.59
     с
    0.58
    思議
    0.58
    ali
    0.57
     acknowledged
    0.57
    POSITIVE LOGITS
    l
    0.81
    "
    0.69
    <0x0D>
    0.68
    n
    0.66
    ב
    0.64
    Area
    0.61
    bereich
    0.61
    m
    0.57
    x
    0.57
    ל
    0.55
    Activations Density 0.011%

    No Known Activations