© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38296
    Prev
    Next
    INDEX
    Explanations

    numerical patterns

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    Roi
    0.40
    Butyl
    0.39
     Fort
    0.39
     Anast
    0.38
    Slash
    0.37
    Gui
    0.36
    imated
    0.36
    氖
    0.36
    Stay
    0.36
     sfr
    0.36
    POSITIVE LOGITS
     ভিত্তিতে
    0.43
     baseURL
    0.38
     leichte
    0.38
     밖에
    0.38
    য়িক
    0.38
     unlocking
    0.37
    北大
    0.37
     приорите
    0.35
    ประเภท
    0.35
     юби
    0.35
    Activations Density 0.002%

    No Known Activations