© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36473
    Prev
    Next
    INDEX
    Explanations

    developed a

    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
    ad
    0.90
    im
    0.85
    р
    0.79
    (
    0.79
    '
    0.73
    ר
    0.73
    x
    0.72
    ill
    0.68
    vi
    0.68
    an
    0.65
    POSITIVE LOGITS
    ۳
    0.64
    ،
    0.58
    ေး
    0.56
     ejac
    0.55
    ૨
    0.55
    、
    0.53
     perempt
    0.52
    dni
    0.52
    の内容
    0.52
    日付
    0.52
    Activations Density 0.000%

    No Known Activations