© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32791
    Prev
    Next
    INDEX
    Explanations

    calculations and computations

    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_7_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
    و
    0.31
    ку
    0.31
    ли
    0.30
    е
    0.30
    ной
    0.28
    ３
    0.28
    ak
    0.28
     poteva
    0.28
    ный
    0.28
    нің
    0.27
    POSITIVE LOGITS
     (
    0.39
     of
    0.33
     to
    0.29
     is
    0.28
     with
    0.28
     kanssa
    0.28
    ار
    0.27
     riches
    0.26
     are
    0.25
     groceries
    0.25
    Activations Density 0.007%

    No Known Activations