© 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. 221749
    Prev
    Next
    INDEX
    Explanations

    write instructions/descriptions

    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
     vessels
    0.47
     revenue
    0.46
     floc
    0.45
     deadline
    0.45
     seeding
    0.45
    स
    0.44
     women
    0.44
     cash
    0.44
     noting
    0.44
    收入
    0.44
    POSITIVE LOGITS
     Tattha
    0.53
    सिंह
    0.51
    ah
    0.50
    скопа
    0.50
    喤
    0.48
     управля
    0.48
     готов
    0.48
    ahari
    0.47
    raved
    0.46
     ट्रॉपिकल
    0.46
    Activations Density 0.000%

    No Known Activations