© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18700
    Prev
    Next
    INDEX
    Explanations

    reached number one charts

    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_34_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
    挟
    0.38
     prese
    0.37
    ும்ப
    0.36
    binghamton
    0.36
     Mustard
    0.34
     expansive
    0.33
    idazol
    0.33
     already
    0.33
     ey
    0.33
    ায
    0.33
    POSITIVE LOGITS
    㷌
    0.38
    曏
    0.37
    Boundary
    0.37
    登上
    0.37
     terminating
    0.37
     गूगल
    0.37
    ChatGPT
    0.36
    Netflix
    0.36
    Google
    0.36
    Applications
    0.35
    Activations Density 0.003%

    No Known Activations