© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178543
    Prev
    Next
    INDEX
    Explanations

    actively

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    稣
    0.45
     glaucoma
    0.41
     dr
    0.40
     порядок
    0.40
     thunderstorm
    0.39
     chuck
    0.39
     pollination
    0.38
     current
    0.37
     vot
    0.37
     chance
    0.37
    POSITIVE LOGITS
    ijiet
    0.39
    mot
    0.38
    悹
    0.37
    વારો
    0.37
    AQ
    0.36
    низ
    0.36
    ventures
    0.36
    हरू
    0.35
    straight
    0.35
    ských
    0.35
    Activations Density 0.007%

    No Known Activations