© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40358
    Prev
    Next
    INDEX
    Explanations

    torch

    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_57_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
    الا
    0.46
    움
    0.42
     Osw
    0.40
     والد
    0.39
    沙漠
    0.39
     Epit
    0.39
    旯
    0.39
     нес
    0.38
    يًا
    0.37
    નેસ
    0.37
    POSITIVE LOGITS
    ı
    0.47
     ie
    0.46
    ie
    0.46
     hr
    0.42
    boston
    0.42
    short
    0.42
    zilla
    0.41
    shmi
    0.41
     hz
    0.41
     boston
    0.40
    Activations Density 0.002%

    No Known Activations