© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 115925
    Prev
    Next
    INDEX
    Explanations

    data, options, rows, series, schema

    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_27_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
     hia
    0.41
     입
    0.41
    雜
    0.39
    біць
    0.38
    歸
    0.38
    사람
    0.38
    Radi
    0.38
    Denovo
    0.37
    려
    0.37
     연구
    0.36
    POSITIVE LOGITS
     actualización
    0.42
     شدم
    0.41
     paix
    0.40
     Pochettino
    0.40
     paz
    0.39
    分页
    0.39
     kesin
    0.38
     menyimpan
    0.38
     caráter
    0.38
     सकारात्मक
    0.37
    Activations Density 0.001%

    No Known Activations