© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39423
    Prev
    Next
    INDEX
    Explanations

    PHP controller or model boilerplate

    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_11_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
     can
    0.52
    u
    0.51
     unveiled
    0.50
    í
    0.50
     has
    0.48
    al
    0.47
    r
    0.47
     nui
    0.47
     Ziegler
    0.47
     či
    0.47
    POSITIVE LOGITS
    氧化
    0.50
    Ва
    0.50
    Sheikh
    0.48
    Know
    0.46
    ༧
    0.46
    Sheila
    0.46
    pering
    0.45
    Too
    0.45
    SpecID
    0.45
    Point
    0.44
    Activations Density 0.001%

    No Known Activations