© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44014
    Prev
    Next
    INDEX
    Explanations

    percent or tax calculation

    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_13_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
    set
    0.45
    ore
    0.43
    व
    0.43
    authentic
    0.42
    $
    0.42
     kwietnia
    0.42
    am
    0.42
    +)$
    0.41
    ac
    0.40
    éré
    0.40
    POSITIVE LOGITS
    Percent
    0.60
     Percent
    0.57
     \%
    0.55
     PERCENT
    0.54
     $\%
    0.54
     (\%)
    0.52
     CENT
    0.49
     Cen
    0.49
     Compounds
    0.48
     Dose
    0.48
    Activations Density 0.021%

    No Known Activations