© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 147457
    Prev
    Next
    INDEX
    Explanations

    0

    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_59_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
     summer
    0.64
     Summer
    0.64
    Summer
    0.64
    summer
    0.59
    暑
    0.59
     여름
    0.57
     zomer
    0.57
    夏
    0.56
    夏の
    0.55
    June
    0.55
    POSITIVE LOGITS
     ۷
    0.42
    ⁷
    0.38
    7
    0.37
     ७
    0.36
     ৭
    0.33
    ៧
    0.32
    ၇
    0.30
    ٧
    0.29
     ८
    0.29
    𝟕
    0.28
    Activations Density 0.000%

    No Known Activations