© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 17535
    Prev
    Next
    INDEX
    Explanations

    async Insert, Get, update, getAll

    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
    策
    0.40
    埒
    0.38
    ismod
    0.38
    Unique
    0.36
    Mod
    0.36
     প্রতিনিধি
    0.36
     уника
    0.36
     sensual
    0.36
     প্রতিনিধ
    0.35
    ^{[\
    0.35
    POSITIVE LOGITS
     pojed
    0.43
     chin
    0.42
     economica
    0.42
     Collapse
    0.41
     collapse
    0.41
    clud
    0.41
    ald
    0.39
     પૈ
    0.39
    oucher
    0.38
     об
    0.38
    Activations Density 0.001%

    No Known Activations