© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207829
    Prev
    Next
    INDEX
    Explanations

    data structures like list, struct, map

    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_20_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
    サイズ
    0.49
     Penet
    0.46
     Size
    0.45
    癃
    0.45
     Sizes
    0.44
    サイズの
    0.44
    ுறு
    0.42
    ભ
    0.41
     Сури
    0.41
     nrow
    0.41
    POSITIVE LOGITS
    tavern
    0.54
    tal
    0.47
    daily
    0.47
     leaving
    0.47
    ोंग
    0.46
    leaving
    0.45
    ْل
    0.45
    čiti
    0.44
    odi
    0.44
    qtt
    0.44
    Activations Density 0.000%

    No Known Activations