© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32474
    Prev
    Next
    INDEX
    Explanations

    contact us

    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
    కు
    0.31
     manifestó
    0.29
     esclusivamente
    0.29
     становится
    0.28
    에게
    0.28
    는
    0.28
     모든
    0.27
     absolutamente
    0.27
     ваших
    0.27
     seguirá
    0.27
    POSITIVE LOGITS
    t
    0.35
    st
    0.35
    c
    0.32
    ak
    0.30
    bouw
    0.30
    of
    0.29
    akad
    0.27
     دو
    0.27
     echt
    0.27
    ob
    0.27
    Activations Density 0.163%

    No Known Activations