© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15856
    Prev
    Next
    INDEX
    Explanations

    simple fraction

    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_40_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
     lem
    0.42
    രോധ
    0.41
     hc
    0.40
    lem
    0.39
    帑
    0.39
     Willis
    0.38
     HC
    0.38
     gre
    0.38
     Samuel
    0.38
    }=(
    0.38
    POSITIVE LOGITS
     fraction
    1.05
     fractions
    1.02
    fraction
    0.95
     fracción
    0.95
     Fraction
    0.95
    Fraction
    0.91
     Fractions
    0.88
    frac
    0.84
     fracciones
    0.82
     frac
    0.79
    Activations Density 0.033%

    No Known Activations