© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 136633
    Prev
    Next
    INDEX
    Explanations

    plural forms / endings

    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_12_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
    0.52
    ut
    0.51
    茶
    0.49
    un
    0.48
    uk
    0.48
    ım
    0.47
    mp
    0.47
    Nep
    0.46
    ");
    0.46
    id
    0.45
    POSITIVE LOGITS
    Ϩ
    0.59
    ση
    0.54
    ρίες
    0.54
     reserve
    0.52
     Reserve
    0.52
    тивные
    0.50
     auctor
    0.50
     reservas
    0.49
     RESERVE
    0.48
     hogares
    0.48
    Activations Density 0.003%

    No Known Activations