© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201466
    Prev
    Next
    INDEX
    Explanations

    inspired by

    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
    ק
    0.70
    к
    0.70
    czeniu
    0.60
    𝗻
    0.60
    𝗸
    0.60
    валися
    0.59
    šení
    0.57
    𝘬
    0.57
    𝗴
    0.57
    ソン
    0.55
    POSITIVE LOGITS
    üt
    0.58
    åll
    0.54
     bulkhead
    0.52
    ått
    0.52
     si
    0.50
     topRight
    0.50
     కథ
    0.50
     hoard
    0.49
     thorac
    0.49
    årt
    0.49
    Activations Density 0.000%

    No Known Activations