© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165471
    Prev
    Next
    INDEX
    Explanations

    once again

    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
    0
    0.53
    в
    0.50
    ٠
    0.49
    卓
    0.46
    x
    0.46
    시아
    0.46
    shi
    0.46
    ۰
    0.44
    тическая
    0.44
    خ
    0.44
    POSITIVE LOGITS
     squre
    0.48
     dobrze
    0.47
    ವರೆ
    0.47
     Burgen
    0.47
     forno
    0.46
     nort
    0.46
     ചെറു
    0.46
     Camaro
    0.46
     limo
    0.46
    erol
    0.46
    Activations Density 0.000%

    No Known Activations