© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44362
    Prev
    Next
    INDEX
    Explanations

    Get FileName, Get Reports, capture energy, Guid child

    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_13_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
     celles
    0.51
    （
    0.49
     الل
    0.48
    АР
    0.48
    atrical
    0.47
     बोर्ड
    0.47
    ipolar
    0.46
    ઇ
    0.46
    rap
    0.46
    ractable
    0.46
    POSITIVE LOGITS
     rightful
    0.45
     Sarge
    0.44
     vineyard
    0.43
     monument
    0.43
    兕
    0.43
     اولمپ
    0.42
     exer
    0.41
     Olympian
    0.40
     ἐν
    0.39
    賓
    0.39
    Activations Density 0.000%

    No Known Activations