© 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. 123940
    Prev
    Next
    INDEX
    Explanations

    tricep dips, stretch, strength

    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
    0.82
     It
    0.70
    em
    0.70
     trich
    0.66
     trident
    0.66
    .
    0.65
    。
    0.65
     Trich
    0.65
     trio
    0.64
     ergibt
    0.64
    POSITIVE LOGITS
    та
    1.10
    ק
    1.09
    지
    1.07
    ку
    1.04
    ει
    1.01
    ס
    0.94
    ди
    0.93
    ва
    0.93
    ки
    0.92
    ुप
    0.92
    Activations Density 0.001%

    No Known Activations