© 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. 10168
    Prev
    Next
    INDEX
    Explanations

    work safety and material 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_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
     pancre
    0.51
     регули
    0.50
     polysaccharides
    0.49
     wykorzyst
    0.48
     igu
    0.48
     stockno
    0.48
     ilust
    0.47
     発
    0.47
     harmonica
    0.47
     steht
    0.47
    POSITIVE LOGITS
    یند
    0.53
    R
    0.48
    ્યો
    0.47
    pada
    0.47
    喁
    0.47
    ings
    0.46
    ok
    0.46
    انا
    0.46
    ène
    0.45
    Mirror
    0.45
    Activations Density 0.025%

    No Known Activations