© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 36275
    Prev
    Next
    INDEX
    Explanations

    cancer, mutations, risk

    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_31_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
    Hep
    0.39
     Seymour
    0.38
    닐
    0.36
     Hep
    0.36
    itada
    0.36
    itado
    0.35
     thr
    0.35
    ogat
    0.35
    phase
    0.34
    Six
    0.34
    POSITIVE LOGITS
     الدوري
    0.36
    Clr
    0.35
    果
    0.35
     inconvenience
    0.34
     Newtown
    0.33
     महंत
    0.33
     hy
    0.33
     rapidity
    0.32
     foci
    0.32
     vict
    0.32
    Activations Density 0.031%

    No Known Activations