© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202180
    Prev
    Next
    INDEX
    Explanations

    explains what that means

    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
    ج
    0.63
    コン
    0.59
    プロ
    0.57
    b
    0.57
    サ
    0.56
    z
    0.54
     プロ
    0.54
    に向
    0.53
    نی
    0.53
    يلي
    0.52
    POSITIVE LOGITS
    TEMPERATURE
    0.61
    ISTANCE
    0.55
    IER
    0.54
     вести
    0.53
    DESCRIPTION
    0.53
    Russia
    0.51
    CURRENT
    0.51
     ảnh
    0.49
    LONDON
    0.49
    ruktur
    0.48
    Activations Density 0.003%

    No Known Activations