© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29104
    Prev
    Next
    INDEX
    Explanations

    peer-to-peer sharing and review

    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_10_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
    ing
    0.95
    a
    0.94
    ee
    0.89
    o
    0.85
    al
    0.82
    e
    0.82
    as
    0.82
     it
    0.80
    MAR
    0.80
    oof
    0.80
    POSITIVE LOGITS
     civilization
    0.80
     peer
    0.78
     peers
    0.78
    க்
    0.76
     volcanic
    0.71
    ystems
    0.71
     class
    0.70
     bourgeois
    0.70
    ために
    0.69
     scandals
    0.68
    Activations Density 0.009%

    No Known Activations