© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7659
    Prev
    Next
    INDEX
    Explanations

    list item delimiters

    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_40_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
     kto
    0.37
    शिया
    0.37
     결과를
    0.36
     행복
    0.36
    CDF
    0.35
     整
    0.35
    apor
    0.35
    cylinder
    0.34
    came
    0.34
    وقف
    0.34
    POSITIVE LOGITS
    倞
    0.42
    𝖊
    0.39
    blico
    0.39
    езд
    0.38
    ปลอด
    0.37
    mson
    0.37
    noon
    0.37
     Hermann
    0.37
     Molina
    0.37
     Maldon
    0.37
    Activations Density 0.000%

    No Known Activations