© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58573
    Prev
    Next
    INDEX
    Explanations

    what genuinely excites

    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_11_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
    </h2>
    0.63
    。
    0.62
    0.59
     forklift
    0.58
    six
    0.57
     eight
    0.56
     bully
    0.55
     federally
    0.54
     glare
    0.54
     hangar
    0.54
    POSITIVE LOGITS
    ב
    0.79
    ب
    0.75
    р
    0.71
     Polaribacter
    0.71
    ר
    0.70
    ס
    0.64
    ർ
    0.64
     परेशानियों
    0.63
    з
    0.63
    ()"
    0.61
    Activations Density 0.004%

    No Known Activations