© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50942
    Prev
    Next
    INDEX
    Explanations

    "sure" followed by "of" or "your"

    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_10_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
    ana
    0.67
    ne
    0.64
    scaping
    0.57
    az
    0.56
    ⁩
    0.54
    ukuran
    0.54
     stadion
    0.54
    ꞌ
    0.54
     be
    0.53
     città
    0.53
    POSITIVE LOGITS
    わり
    0.59
    ト
    0.56
    お
    0.56
    وین
    0.55
    いて
    0.55
    Residual
    0.54
    وسی
    0.54
    بح
    0.54
    中で
    0.52
    Sick
    0.52
    Activations Density 0.000%

    No Known Activations