© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91664
    Prev
    Next
    INDEX
    Explanations

    this code

    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_11_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
    드
    0.55
    어
    0.54
    н
    0.52
    மய
    0.51
    ولی
    0.50
    堇
    0.50
    ник
    0.50
     perteneciente
    0.49
    น
    0.49
    ொ
    0.49
    POSITIVE LOGITS
    en
    0.61
    et
    0.57
    were
    0.56
     find
    0.55
     wget
    0.55
     from
    0.55
     ('
    0.55
     gooey
    0.55
    hen
    0.55
    up
    0.54
    Activations Density 0.002%

    No Known Activations