© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86384
    Prev
    Next
    INDEX
    Explanations

    code delimiters and various languages

    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_18_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
    Client
    0.45
    Ж
    0.43
    Process
    0.41
    :#
    0.40
    Worldwide
    0.39
    П
    0.38
    Bl
    0.38
     cloud
    0.38
    О
    0.38
    Del
    0.38
    POSITIVE LOGITS
     გამოყენ
    0.46
     subtração
    0.45
     Choisissez
    0.44
     Alg
    0.43
     giochi
    0.43
    ্নের
    0.43
     గే
    0.43
    游戏的
    0.42
     Lua
    0.42
    腖
    0.42
    Activations Density 0.000%

    No Known Activations