© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38212
    Prev
    Next
    INDEX
    Explanations

    programming concepts and code structures

    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_3_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
    s
    0.83
    ’
    0.82
    d
    0.76
    ITIES
    0.66
    detection
    0.65
    ärer
    0.64
     in
    0.63
    ের
    0.63
     Interiors
    0.62
    tr
    0.62
    POSITIVE LOGITS
    い
    0.75
    ת
    0.74
     penultimate
    0.73
    ing
    0.70
    टिंग
    0.66
    你
    0.66
     rame
    0.66
     minivan
    0.65
     drugih
    0.65
     νέα
    0.64
    Activations Density 0.024%

    No Known Activations