© 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. 46458
    Prev
    Next
    INDEX
    Explanations

    early 20th century

    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
    on
    1.06
     It
    0.99
    that
    0.98
    an
    0.97
    un
    0.95
     on
    0.95
    l
    0.91
    ،
    0.91
    ，
    0.88
    og
    0.87
    POSITIVE LOGITS
    স
    0.95
    ده
    0.91
    ف
    0.88
    स
    0.84
    জ
    0.80
     proliferative
    0.78
     intermediaries
    0.76
    ('%
    0.76
     offences
    0.75
    ئیں۔
    0.75
    Activations Density 0.003%

    No Known Activations