© 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. 76214
    Prev
    Next
    INDEX
    Explanations

    density and pressure in physical contexts

    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
     selection
    0.74
     selecting
    0.72
     sele
    0.70
    selection
    0.69
     Selection
    0.68
     выбо
    0.68
    Selection
    0.67
    選
    0.67
     selección
    0.66
     selezione
    0.64
    POSITIVE LOGITS
    PathVariable
    0.39
     sidelined
    0.36
     follower
    0.36
    Excluded
    0.36
     avatars
    0.36
    𝙫
    0.35
     emails
    0.35
     ادی
    0.35
     પ્રમાણે
    0.35
     presumed
    0.34
    Activations Density 0.039%

    No Known Activations