© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229815
    Prev
    Next
    INDEX
    Explanations

    interesting

    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_6_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
    o
    1.02
    i
    0.82
    in
    0.64
    ।
    0.64
    ड
    0.64
    。
    0.61
     seascape
    0.60
     vowel
    0.58
    d
    0.58
     subnet
    0.58
    POSITIVE LOGITS
    ير
    0.78
    ó
    0.76
     Și
    0.73
     Á
    0.70
     R
    0.70
    ând
    0.70
     Gö
    0.70
     É
    0.69
     C
    0.68
     Ä
    0.68
    Activations Density 0.003%

    No Known Activations