© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126580
    Prev
    Next
    INDEX
    Explanations

    confusion matrix

    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_3_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
     decentral
    0.67
     जिसके
    0.61
     ﺍﻟ
    0.61
     发表于
    0.61
    ﺪ
    0.60
     of
    0.58
     밝혔
    0.57
     sprouting
    0.57
     trampled
    0.56
    ία
    0.55
    POSITIVE LOGITS
    is
    0.85
    ن
    0.84
    ли
    0.79
    od
    0.69
    ন
    0.68
    ad
    0.68
    యన
    0.66
    <0x98>
    0.64
    不仅
    0.64
    '
    0.63
    Activations Density 0.000%

    No Known Activations