© 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. 195292
    Prev
    Next
    INDEX
    Explanations

    code and 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_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
    tete
    0.40
     ठहरा
    0.38
     Bz
    0.38
    郅
    0.38
    Chim
    0.37
    thirty
    0.37
    氪
    0.37
    zert
    0.36
    ZrO
    0.36
    Bx
    0.35
    POSITIVE LOGITS
    l
    0.47
    ellus
    0.46
    ल
    0.44
    ل
    0.43
    ced
    0.43
    गल
    0.42
    uido
    0.42
     CED
    0.42
    ids
    0.41
    lid
    0.41
    Activations Density 0.007%

    No Known Activations