© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196978
    Prev
    Next
    INDEX
    Explanations

    aim of the study was to

    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_27_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
    กำ
    0.44
     تمامی
    0.40
     phép
    0.39
     eletr
    0.38
    Coffee
    0.38
    ГИ
    0.37
    िटेशन
    0.37
    此
    0.37
    厸
    0.36
    지지
    0.36
    POSITIVE LOGITS
     당시
    0.46
     damals
    0.45
    当時
    0.40
     তৎকালীন
    0.39
    voja
    0.39
     cousins
    0.38
    ordi
    0.38
     damal
    0.37
     Emb
    0.36
     Forecast
    0.36
    Activations Density 0.000%

    No Known Activations