© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 79681
    Prev
    Next
    INDEX
    Explanations

    section headers

    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_53_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
    ()));
    0.43
    ࿐
    0.39
    ulier
    0.39
     เหล
    0.38
    เหล
    0.37
     menjawab
    0.37
    reportBody
    0.36
    hood
    0.36
    Rt
    0.35
     veritable
    0.35
    POSITIVE LOGITS
    支
    0.41
     ople
    0.39
     Pache
    0.38
    மையாக
    0.37
     sè
    0.37
    rollup
    0.36
     Cred
    0.36
     Chester
    0.36
     صدا
    0.36
     Plugin
    0.36
    Activations Density 0.029%

    No Known Activations