© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 43091
    Prev
    Next
    INDEX
    Explanations

    Aquinas

    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
    <0xBB>
    0.63
    نا
    0.62
    ндә
    0.59
    <0xA5>
    0.59
    ående
    0.59
    вами
    0.58
    2
    0.57
     manger
    0.57
    AT
    0.57
    <0xBE>
    0.56
    POSITIVE LOGITS
    ling
    0.64
    li
    0.62
     in
    0.59
    llen
    0.59
    ri
    0.57
    lies
    0.57
    ra
    0.56
    レッド
    0.55
     toneladas
    0.54
    lu
    0.54
    Activations Density 0.001%

    No Known Activations