© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54132
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and variables

    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_30_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
    铖
    0.33
    OOP
    0.33
    PTV
    0.32
    Effect
    0.31
    Electrical
    0.31
    Per
    0.30
     anzu
    0.30
    Management
    0.29
     Inverse
    0.29
    |^{-
    0.29
    POSITIVE LOGITS
     entschieden
    0.35
     দম
    0.32
    荨
    0.32
     decid
    0.31
     ожида
    0.31
     い
    0.31
     अड
    0.31
     decided
    0.31
     sür
    0.31
     occupe
    0.31
    Activations Density 0.000%

    No Known Activations