© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 168250
    Prev
    Next
    INDEX
    Explanations

    divided

    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_56_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
    開
    1.29
    开
    1.24
     opening
    1.23
     Opening
    1.09
    Opening
    1.09
     开
    1.05
    opening
    1.02
    开了
    0.94
     khai
    0.92
     åp
    0.92
    POSITIVE LOGITS
    裆
    0.42
    early
    0.42
    起来
    0.41
    cze
    0.40
    ší
    0.40
    ístico
    0.40
    перы
    0.40
    டம்
    0.39
     early
    0.38
     up
    0.37
    Activations Density 0.004%

    No Known Activations