© 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. 176491
    Prev
    Next
    INDEX
    Explanations

    Captain

    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
    weave
    0.46
    ᐃ
    0.43
    そば
    0.39
    யோ
    0.39
    rama
    0.39
    sPath
    0.38
    weaver
    0.38
    蹉
    0.38
    economy
    0.37
    ছাত্র
    0.37
    POSITIVE LOGITS
     Đông
    0.44
     afternoons
    0.42
     East
    0.40
     Ch
    0.38
     knocking
    0.38
     Franco
    0.38
    त्रियों
    0.37
     outlier
    0.37
     artistic
    0.37
     Christians
    0.37
    Activations Density 0.000%

    No Known Activations