© 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. 220123
    Prev
    Next
    INDEX
    Explanations

    links to github or pub

    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
     emitters
    0.39
     breeder
    0.37
     lenses
    0.37
    併
    0.36
    ␥
    0.36
     succesfully
    0.36
    갑습니다
    0.35
    Loren
    0.35
     반영
    0.34
     Lorenz
    0.34
    POSITIVE LOGITS
     Battle
    0.46
    搁
    0.43
    нням
    0.41
     Craigslist
    0.40
     રૂપ
    0.39
     SDN
    0.39
     Mostly
    0.38
     Manifest
    0.38
    宀
    0.38
     REST
    0.37
    Activations Density 0.000%

    No Known Activations