© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154490
    Prev
    Next
    INDEX
    Explanations

    say "8"

    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_60_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
     ۸
    0.72
     eighties
    0.71
    ৮
    0.68
    ۸
    0.67
     ৮
    0.66
     eighty
    0.64
    
    0.61
     八
    0.60
     Eighty
    0.60
     huit
    0.59
    POSITIVE LOGITS
    6
    0.83
    5
    0.75
     sixth
    0.71
    4
    0.66
    ٦
    0.60
    ６
    0.59
    sixth
    0.59
     six
    0.57
     Sixth
    0.56
     여섯
    0.55
    Activations Density 0.002%

    No Known Activations