© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212535
    Prev
    Next
    INDEX
    Explanations

    base on

    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_5_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
    -
    1.36
    ao
    1.13
     encont
    1.11
    i
    1.09
    دت
    0.95
     essais
    0.95
     cuidados
    0.95
     padrões
    0.94
    čiau
    0.93
     άλλα
    0.93
    POSITIVE LOGITS
    ра
    1.05
    ות
    0.99
    о
    0.95
     for
    0.90
    .}
    0.90
    е
    0.89
    রা
    0.85
    OW
    0.83
    য়োজনীয়
    0.83
    ु
    0.83
    Activations Density 0.008%

    No Known Activations