© 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. 213755
    Prev
    Next
    INDEX
    Explanations

    [

    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
     Networking
    0.39
     Stochastic
    0.38
    不停
    0.38
    ਕਾਰੀ
    0.38
    riends
    0.37
    놉
    0.37
    stride
    0.37
     Setting
    0.36
    を設定
    0.36
    ⑥
    0.36
    POSITIVE LOGITS
     mobility
    0.40
     Prab
    0.40
    TS
    0.38
     TS
    0.38
    増
    0.38
    驮
    0.37
    mobility
    0.37
     eyelashes
    0.37
    整體
    0.37
    overall
    0.36
    Activations Density 0.003%

    No Known Activations