© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 124365
    Prev
    Next
    INDEX
    Explanations

    icon usage in code

    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_37_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
    콤
    0.40
    န့်
    0.38
    了一声
    0.38
     return
    0.38
     thalassemia
    0.37
     symptoms
    0.37
     Intelligent
    0.37
     номер
    0.37
    智能
    0.37
     Nº
    0.37
    POSITIVE LOGITS
    |>
    0.38
    HEA
    0.38
    STOP
    0.37
    䟺
    0.37
     النف
    0.36
    Dar
    0.36
    Ку
    0.36
    Lyon
    0.36
    pron
    0.35
     Larry
    0.35
    Activations Density 0.000%

    No Known Activations