© 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. 155671
    Prev
    Next
    INDEX
    Explanations

    I

    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
     جما
    0.37
     বাছাই
    0.37
     grouping
    0.35
    履
    0.35
     coarsely
    0.35
     පා
    0.34
     mse
    0.34
     feet
    0.34
     Hass
    0.34
     dar
    0.34
    POSITIVE LOGITS
     Geos
    0.42
     நானும்
    0.42
     Quadrupèdes
    0.42
     Automobiles
    0.39
    痙
    0.39
     विडियो
    0.39
     Subsequent
    0.38
    ંત્રણ
    0.38
    兩人
    0.38
     ICH
    0.38
    Activations Density 0.040%

    No Known Activations