© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31333
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by words

    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_31_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
    및
    0.68
    及
    0.65
     및
    0.63
    及び
    0.59
     һәм
    0.56
    および
    0.55
     आणि
    0.54
     ও
    0.53
     மற்றும்
    0.52
     および
    0.52
    POSITIVE LOGITS
     NSMutable
    0.38
     ਨ
    0.36
    ቱ
    0.35
    వరి
    0.34
    akra
    0.34
    Tl
    0.34
    thus
    0.33
     faiblement
    0.33
    FileUtils
    0.33
    越来越多
    0.33
    Activations Density 0.136%

    No Known Activations