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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172707
    Prev
    Next
    INDEX
    Explanations

    data structure collections

    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_20_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
    镊
    0.44
     racemic
    0.43
    化学
    0.43
     வன
    0.43
    ໕
    0.43
    äure
    0.41
     Neuroscience
    0.41
     Bounds
    0.41
    ‐
    0.41
     ecology
    0.40
    POSITIVE LOGITS
    Ultimate
    0.45
     telenov
    0.44
    ക്കിയത്
    0.43
     reverted
    0.40
     promos
    0.38
     pampered
    0.38
    vak
    0.38
     destined
    0.38
    Cuando
    0.38
    Herk
    0.38
    Activations Density 0.000%

    No Known Activations