© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 159112
    Prev
    Next
    INDEX
    Explanations

    Claude or Cleric

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    atsch
    0.47
    hematic
    0.40
    Hann
    0.40
    சன்
    0.40
    getElement
    0.38
    Mat
    0.38
    mate
    0.38
    荻
    0.38
    igts
    0.37
    ശന
    0.37
    POSITIVE LOGITS
     अलंकार
    0.39
     convexe
    0.39
     Lank
    0.37
     lon
    0.36
    वर्तन
    0.36
    ENCI
    0.36
    वृद्धि
    0.36
    υκ
    0.36
     اولم
    0.36
     কোর
    0.36
    Activations Density 0.002%

    No Known Activations