© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 41-GEMMASCOPE-2-TRANSCODER-262K
    4. 64180
    Prev
    Next
    INDEX
    Explanations

    julia code

    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_41_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
    留意
    0.40
     satd
    0.40
    訴
    0.38
    اتھ
    0.37
    Pennsylvania
    0.37
    )`;
    0.37
    startswith
    0.37
     retrouver
    0.37
    Uttar
    0.37
    尬
    0.36
    POSITIVE LOGITS
     Pre
    0.48
     gaz
    0.45
    Pre
    0.45
     Post
    0.39
     pre
    0.39
    post
    0.38
     post
    0.38
     Kuna
    0.38
    gaz
    0.37
     Streams
    0.37
    Activations Density 0.000%

    No Known Activations