© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57663
    Prev
    Next
    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    AS
    1.00
    IA
    0.91
    S
    0.88
    D
    0.86
    EC
    0.84
    IC
    0.83
    OC
    0.83
    H
    0.82
    AT
    0.82
    ET
    0.82
    POSITIVE LOGITS
    for
    0.50
    mango
    0.50
    may
    0.50
    cubic
    0.49
    wa
    0.48
    autor
    0.47
    mast
    0.47
    raspberry
    0.47
    bord
    0.46
    such
    0.46
    Activations Density 0.005%

    No Known Activations