© 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. 155323
    Prev
    Next
    INDEX
    Explanations

    body tag

    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
    ป
    0.36
    プロ
    0.36
    َنْ
    0.35
    ಿದ್ದಾರೆ
    0.35
    KB
    0.34
     பாரன்ஹீ
    0.34
     プロ
    0.34
    roffen
    0.34
    ruppen
    0.34
    èi
    0.33
    POSITIVE LOGITS
    Nos
    0.50
     nos
    0.48
     Nos
    0.47
    |<
    0.41
     (<
    0.41
     குறித்த
    0.40
    吿
    0.40
     Number
    0.40
     Nauk
    0.40
     NOS
    0.39
    Activations Density 0.001%

    No Known Activations