© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 51-GEMMASCOPE-2-TRANSCODER-262K
    7. 67314
    Prev
    Next
    INDEX
    Explanations

    academic acronyms

    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_51_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
    achts
    0.46
    ться
    0.39
    otemporal
    0.38
    itized
    0.37
    ھا
    0.36
     フロ
    0.36
    猩
    0.36
     passenger
    0.36
    枟
    0.36
    tutorial
    0.36
    POSITIVE LOGITS
    OSU
    0.48
    NU
    0.46
    щу
    0.45
     Raju
    0.45
    ANU
    0.44
    osu
    0.44
    њу
    0.44
    жу
    0.44
    anju
    0.44
     IU
    0.43
    Activations Density 0.000%

    No Known Activations