© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79314
    Prev
    Next
    INDEX
    Explanations

    I see you

    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_31_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
    RDS
    0.38
    㗊
    0.37
    py
    0.35
     LIKE
    0.35
    rack
    0.35
    abbani
    0.34
     благодаря
    0.34
    icur
    0.34
    Identifying
    0.34
     giấc
    0.34
    POSITIVE LOGITS
    娣
    0.38
     ski
    0.37
     windings
    0.37
     seep
    0.37
     windscreen
    0.36
    häuse
    0.36
     skis
    0.36
     projectors
    0.36
     contends
    0.35
     القسم
    0.35
    Activations Density 0.002%

    No Known Activations