© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11945
    Prev
    Next
    INDEX
    Explanations

    SETI detection range

    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
     -
    0.60
     la
    0.49
    是
    0.46
    0.44
    :
    0.43
     é
    0.43
    性
    0.43
    ized
    0.43
    ни
    0.43
     is
    0.42
    POSITIVE LOGITS
     वोल्टेज
    0.56
     आइकन
    0.55
     Phas
    0.53
     gota
    0.52
     மடங்கு
    0.52
    🫰
    0.52
    ফি
    0.52
     Hatton
    0.51
     एक्चु
    0.50
     jotka
    0.49
    Activations Density 0.079%

    No Known Activations