© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 62581
    Prev
    Next
    INDEX
    Explanations

    finer fibers

    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_2_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
    ↵
    0.98
    는
    0.92
     determinada
    0.89
    igkeiten
    0.84
     mojo
    0.84
     esté
    0.83
     أن
    0.82
     просты
    0.82
    говой
    0.82
     الك
    0.81
    POSITIVE LOGITS
    ’
    1.31
    It
    1.14
     It
    1.13
    ी
    1.09
    to
    1.07
    '
    1.07
    the
    1.05
    rom
    0.99
    ל
    0.96
    மாக
    0.95
    Activations Density 0.005%

    No Known Activations