© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 216906
    Prev
    Next
    INDEX
    Explanations

    punctuation marks

    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_47_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
     नका
    0.42
     boardwalk
    0.41
     ออก
    0.39
     絵
    0.39
     Пас
    0.39
    cock
    0.39
    Fizz
    0.38
    тування
    0.38
    бал
    0.38
    えない
    0.37
    POSITIVE LOGITS
     Consc
    0.45
     bewust
    0.44
     conscientes
    0.42
     conscious
    0.41
     acutely
    0.39
     mindful
    0.38
    ↣
    0.38
    意识
    0.38
    ร้อน
    0.38
     ஞான
    0.38
    Activations Density 0.003%

    No Known Activations