© 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
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 200916
    Prev
    Next
    INDEX
    Explanations

    Saul and Samuel

    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_12_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
     করিয়৷
    0.54
     opio
    0.54
    XPath
    0.52
    Salmon
    0.51
     matroid
    0.50
     ulc
    0.50
    ApiClient
    0.49
    expat
    0.48
    Chol
    0.48
    Rover
    0.48
    POSITIVE LOGITS
    时
    0.53
    ق
    0.49
     Remote
    0.48
    ing
    0.46
     Close
    0.44
    热
    0.44
    ká
    0.44
    by
    0.44
     may
    0.43
     circulated
    0.43
    Activations Density 0.000%

    No Known Activations