© 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. 39760
    Prev
    Next
    INDEX
    Explanations

    Cathedral or Act

    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
    I
    0.92
    A
    0.72
    ی
    0.72
    s
    0.67
    IJ
    0.67
    Eq
    0.64
    Ig
    0.60
    Ay
    0.59
     be
    0.58
    IK
    0.58
    POSITIVE LOGITS
    äns
    0.66
    itä
    0.61
    fär
    0.59
    ला
    0.58
    illä
    0.58
    farm
    0.57
    issä
    0.57
    ouring
    0.57
    al
    0.55
    gados
    0.55
    Activations Density 0.001%

    No Known Activations