© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258547
    Prev
    Next
    INDEX
    Explanations

    code punctuation and operators

    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_22_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
     dimensional
    0.29
    uğ
    0.29
     cun
    0.29
    ере
    0.28
    :
    0.28
     closely
    0.27
     verbunden
    0.27
     मर्द
    0.27
    🇹
    0.27
     pilgrims
    0.26
    POSITIVE LOGITS
    verk
    0.32
    ចាយ
    0.29
     जाप
    0.28
     தவிர்க்க
    0.28
    रोक्त
    0.27
    exhaustive
    0.27
    voiced
    0.27
    ko
    0.27
     ज्यादातर
    0.27
    市立
    0.27
    Activations Density 0.002%

    No Known Activations