© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 205096
    Prev
    Next
    INDEX
    Explanations

    extract data units

    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_46_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
     जैसी
    0.39
    ysty
    0.39
     fonction
    0.38
    ijk
    0.38
     Fonction
    0.37
     Έ
    0.37
    とか
    0.36
    機能
    0.36
     Motorsport
    0.35
    *
    0.35
    POSITIVE LOGITS
     attached
    0.63
    attached
    0.60
     attach
    0.60
    附
    0.60
     Attached
    0.58
     attaching
    0.56
    attach
    0.53
    Attach
    0.52
     append
    0.52
    Attached
    0.50
    Activations Density 0.002%

    No Known Activations