© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 15303
    Prev
    Next
    INDEX
    Explanations

    DB

    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_15_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
    저
    0.47
    今日の
    0.47
     sixteenth
    0.46
    if
    0.46
    OGRAPHIC
    0.45
    微笑
    0.45
    //=
    0.45
     已
    0.45
    只想
    0.45
    雾
    0.45
    POSITIVE LOGITS
    leva
    0.61
    bahn
    0.59
     vanwege
    0.59
    gaan
    0.52
    lems
    0.51
     Cannes
    0.50
    logne
    0.49
    𝕝
    0.49
    maan
    0.49
    Bahn
    0.49
    Activations Density 0.000%

    No Known Activations