© 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. 75403
    Prev
    Next
    INDEX
    Explanations

    publish / published

    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
    ድረ
    0.37
    Ầ
    0.35
     capped
    0.35
     jun
    0.34
    ಗ್
    0.34
    ലേ
    0.34
     जून
    0.34
     competency
    0.34
     stagnant
    0.34
    >&
    0.34
    POSITIVE LOGITS
    Publish
    0.65
     Publishing
    0.64
     publishing
    0.63
    publishing
    0.62
     publishes
    0.60
     gepub
    0.60
    published
    0.59
     publish
    0.59
     Publish
    0.57
    publish
    0.57
    Activations Density 0.000%

    No Known Activations