© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35069
    Prev
    Next
    INDEX
    Explanations

    editable mode, git, make

    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_31_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
     بقي
    0.39
     rearranged
    0.36
     wasn
    0.34
     முக
    0.34
     epit
    0.34
     sailing
    0.33
     ROUND
    0.33
    손
    0.33
     reorganized
    0.32
     Clause
    0.32
    POSITIVE LOGITS
     spectators
    0.35
    Kent
    0.34
     flexibly
    0.34
    篁
    0.34
     wrestlers
    0.34
    相対
    0.33
    ično
    0.32
     extradition
    0.32
     principle
    0.32
    Editable
    0.32
    Activations Density 0.005%

    No Known Activations