© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200184
    Prev
    Next
    INDEX
    Explanations

    sake

    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
    蕞
    0.54
    金额
    0.53
    小說
    0.52
     годов
    0.51
    ὑ
    0.50
     একত্রে
    0.50
     transcripts
    0.47
     సంస్థ
    0.47
     дости
    0.46
    餐
    0.46
    POSITIVE LOGITS
    i
    0.61
    in
    0.58
     sesu
    0.54
     You
    0.50
    u
    0.50
     Flan
    0.48
     Toggle
    0.47
    И
    0.47
    ნის
    0.46
     Type
    0.46
    Activations Density 0.001%

    No Known Activations