© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13872
    Prev
    Next
    INDEX
    Explanations

    Xbox One

    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
    ances
    0.53
    ces
    0.53
     გარ
    0.52
     ក
    0.51
    As
    0.49
     og
    0.49
    ants
    0.47
    cept
    0.47
    ounded
    0.47
    Musik
    0.47
    POSITIVE LOGITS
    밂
    0.72
     otvore
    0.57
     Lomond
    0.55
     nhanh
    0.53
     ICM
    0.53
     ያላቸው
    0.53
    לט
    0.52
     climático
    0.52
     Dwyer
    0.52
    ಳ
    0.52
    Activations Density 0.004%

    No Known Activations