© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39230
    Prev
    Next
    INDEX
    Explanations

    daily work or practice

    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_3_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
    ن
    0.64
     eighties
    0.63
    न
    0.62
    。
    0.62
     London
    0.61
    他的
    0.60
     hospital
    0.60
     England
    0.58
     memorandum
    0.58
    O
    0.57
    POSITIVE LOGITS
    л
    0.83
    ни
    0.75
    т
    0.71
    зву
    0.68
    све
    0.66
    dz
    0.66
    عية
    0.65
    к
    0.64
    ປະກອບ
    0.64
    rilor
    0.63
    Activations Density 0.007%

    No Known Activations