© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 12369
    Prev
    Next
    INDEX
    Explanations

    don't really verb

    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
    number
    0.77
     blod
    0.65
     stoi
    0.63
    blooded
    0.62
    m
    0.57
    column
    0.55
    execute
    0.54
     number
    0.54
    k
    0.54
    build
    0.53
    POSITIVE LOGITS
     hábitos
    0.62
    ের
    0.62
    ейчас
    0.57
     tradicionales
    0.57
    !’
    0.55
    ман
    0.55
     prácticas
    0.55
    ῾
    0.54
    ้น
    0.52
     Ahora
    0.51
    Activations Density 0.001%

    No Known Activations