© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9962
    Prev
    Next
    INDEX
    Explanations

    report, poured, cuts, bench, begin

    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_13_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
     Dylan
    0.56
     Declan
    0.56
     Hau
    0.55
     rahul
    0.54
    ￭
    0.54
     행동
    0.53
    abhavo
    0.53
     alcançar
    0.52
     atacar
    0.52
     घटस्फोट
    0.52
    POSITIVE LOGITS
    ق
    0.59
    دي
    0.58
    ijks
    0.57
    ANDS
    0.51
    sächlich
    0.49
    Colorful
    0.48
    يع
    0.47
    ছে
    0.47
    ijke
    0.46
    اعت
    0.46
    Activations Density 0.000%

    No Known Activations