© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86925
    Prev
    Next
    INDEX
    Explanations

    understandable why you

    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_23_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
    ИН
    0.46
    细胞
    0.43
     verstär
    0.43
     cells
    0.41
     hạn
    0.41
    萸
    0.39
    ств
    0.38
     बाब
    0.38
    бры
    0.38
     праз
    0.38
    POSITIVE LOGITS
     Fleece
    0.38
    Ṕ
    0.37
    ache
    0.36
     Lowest
    0.36
     sort
    0.35
    みが
    0.35
     conflitto
    0.35
    Ģ
    0.35
     Piv
    0.34
    Referencias
    0.34
    Activations Density 0.002%

    No Known Activations