© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13421
    Prev
    Next
    INDEX
    Explanations

    original content or concepts

    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_13_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
     quantità
    0.33
     наук
    0.30
     fluxo
    0.29
     precipitation
    0.29
     lipids
    0.29
     synergy
    0.29
     στο
    0.29
    ू
    0.29
     precipit
    0.29
     доходов
    0.28
    POSITIVE LOGITS
    ph
    0.37
    świet
    0.31
    ach
    0.31
    Simple
    0.31
    blem
    0.30
    van
    0.30
    pl
    0.30
    bake
    0.29
    bild
    0.29
    abel
    0.29
    Activations Density 0.019%

    No Known Activations