© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 196209
    Prev
    Next
    INDEX
    Explanations

    digits followed by punctuation

    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_15_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
    SRPI
    0.52
    。)
    0.50
     осві
    0.47
    )’
    0.46
    atoon
    0.46
    FAI
    0.46
    ёз
    0.45
     두
    0.45
     نمی‌
    0.44
    Two
    0.43
    POSITIVE LOGITS
     anni
    0.64
     na
    0.59
     pais
    0.59
     laranja
    0.58
     nella
    0.57
    kiego
    0.57
     questione
    0.57
     sagittis
    0.55
    issance
    0.55
     quindi
    0.55
    Activations Density 0.003%

    No Known Activations