© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 206710
    Prev
    Next
    INDEX
    Explanations

    starting at time markers (0:30-1:30)

    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_19_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
    进制
    0.48
     dernière
    0.46
    V
    0.46
    两侧
    0.46
     Haskell
    0.44
     Chemie
    0.43
    嶅
    0.43
     Sommers
    0.42
    quers
    0.42
     As
    0.42
    POSITIVE LOGITS
     يمكنك
    0.49
    patent
    0.45
    ⵥ
    0.45
    کس
    0.43
    哪里
    0.42
     ہوگئی
    0.41
     smtp
    0.41
     frugal
    0.40
     excitement
    0.40
    गम
    0.40
    Activations Density 0.002%

    No Known Activations