© 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. 14692
    Prev
    Next
    INDEX
    Explanations

    pronunciation and tones

    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
    t
    0.64
     you
    0.60
     contradicted
    0.60
     rezultat
    0.55
     muszą
    0.54
    volution
    0.51
    Ⅸ
    0.51
     membantu
    0.50
     αλλά
    0.50
     Halb
    0.50
    POSITIVE LOGITS
    ᄑ
    0.63
    👽
    0.60
    ᄉ
    0.52
     }{}_{\
    0.51
    的
    0.51
    슴
    0.51
    Congressional
    0.51
    '$\
    0.51
    Gig
    0.50
    يلة
    0.50
    Activations Density 0.017%

    No Known Activations