© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46321
    Prev
    Next
    INDEX
    Explanations

    scrape down sides

    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_13_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
     mickey
    0.45
    0
    0.43
    ใหม่
    0.43
    ଈ
    0.42
     écrire
    0.41
     cript
    0.40
     изменений
    0.40
     potrebbero
    0.40
     Tokens
    0.40
     ouvre
    0.39
    POSITIVE LOGITS
    ويه
    0.49
    o
    0.47
    و
    0.46
     cytotoxic
    0.45
    ويم
    0.45
    asign
    0.44
     within
    0.43
    幼
    0.43
     confocal
    0.41
     Jena
    0.40
    Activations Density 0.000%

    No Known Activations