© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195587
    Prev
    Next
    INDEX
    Explanations

    back

    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_46_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
     recognizing
    0.41
    eled
    0.40
    解決
    0.38
     lø
    0.38
     法
    0.38
     reconocer
    0.38
    感が
    0.38
    rekli
    0.38
    kule
    0.37
     감
    0.37
    POSITIVE LOGITS
     cheat
    0.39
     Simultaneous
    0.38
     deix
    0.38
    ानु
    0.38
     Hilbert
    0.37
     simultaneous
    0.36
     cyclical
    0.35
     cheating
    0.35
    ိပ်
    0.35
    သက်
    0.34
    Activations Density 0.000%

    No Known Activations