© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35559
    Prev
    Next
    INDEX
    Explanations

    goes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     arena
    0.43
     تای
    0.40
    ječ
    0.40
     V
    0.39
    мона
    0.39
    瀘
    0.38
    າວ
    0.36
     Rena
    0.36
     تار
    0.35
    ナイ
    0.35
    POSITIVE LOGITS
    کار
    0.38
    ซ์
    0.37
    ROLE
    0.37
    応
    0.37
    Oy
    0.37
    Bk
    0.36
    staging
    0.36
    Gü
    0.36
    ubo
    0.36
    BSD
    0.35
    Activations Density 0.005%

    No Known Activations