© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51049
    Prev
    Next
    INDEX
    Explanations

    formatting and code

    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_55_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
    ﹐
    0.41
     היה
    0.38
     उत्तरी
    0.37
     росій
    0.37
     коюмдары
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.36
     യൂ
    0.36
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.35
     일반
    0.35
     মেডিকেল
    0.35
    POSITIVE LOGITS
    kh
    0.37
    ux
    0.35
    genstein
    0.35
    ior
    0.35
    bek
    0.35
     ensu
    0.35
    inser
    0.34
    others
    0.33
    ge
    0.33
    imming
    0.32
    Activations Density 0.027%

    No Known Activations