© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46378
    Prev
    Next
    INDEX
    Explanations

    sunny weather

    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_10_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
     Saltar
    0.25
     А
    0.24
    av
    0.23
    u
    0.23
    ad
    0.23
    ot
    0.22
     Kỳ
    0.22
     Ј
    0.21
     +
    0.21
     "
    0.21
    POSITIVE LOGITS
    กัน
    0.21
     encontro
    0.21
    ל
    0.21
    是
    0.20
    家に
    0.20
     dirige
    0.20
    เก็บ
    0.19
    س
    0.19
    エ
    0.19
    ه
    0.19
    Activations Density 0.013%

    No Known Activations