© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195913
    Prev
    Next
    INDEX
    Explanations

    year-over-year comparisons

    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_4_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
    in
    0.55
    s
    0.53
    ا
    0.52
    ים
    0.47
    u
    0.46
    er
    0.44
    at
    0.44
    ों
    0.42
    en
    0.41
    is
    0.40
    POSITIVE LOGITS
    S
    0.33
     ваш
    0.30
     zespo
    0.29
    E
    0.29
     sprawd
    0.29
     préciser
    0.29
     tejido
    0.28
     viejo
    0.28
     wygl
    0.28
     modele
    0.27
    Activations Density 0.001%

    No Known Activations