© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 202403
    Prev
    Next
    INDEX
    Explanations

    closing code block

    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_37_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
    渾
    0.40
    ǃ
    0.39
    örper
    0.37
    hnung
    0.37
    запа
    0.37
    genomen
    0.37
     történ
    0.37
     Routing
    0.36
     rappresenta
    0.36
    сат
    0.36
    POSITIVE LOGITS
     forKey
    0.39
     Princess
    0.36
     রাখার
    0.36
    δώ
    0.35
    뎌
    0.35
    enix
    0.34
     princess
    0.34
     princesa
    0.34
     podr
    0.33
     উঠিয়া
    0.33
    Activations Density 0.000%

    No Known Activations