© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23875
    Prev
    Next
    INDEX
    Explanations

    DFS or short

    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_56_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
    有关
    0.60
    有關
    0.56
     በመ
    0.41
    诸
    0.40
    上面
    0.37
    要把
    0.37
    要
    0.36
     সমু
    0.35
     በሚ
    0.35
    ermann
    0.35
    POSITIVE LOGITS
     prioritise
    0.40
    Simplified
    0.39
     podrás
    0.39
    :-)
    0.39
     tocó
    0.38
    会不会
    0.36
    Chú
    0.36
    Bare
    0.35
    য়েড
    0.35
    曈
    0.35
    Activations Density 0.003%

    No Known Activations