© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201685
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    死亡
    0.37
     Rotate
    0.37
     Academic
    0.36
    āya
    0.35
    流
    0.35
    one
    0.35
    sat
    0.35
    prices
    0.35
    sure
    0.35
    Rotate
    0.35
    POSITIVE LOGITS
     enhancing
    0.42
    ojis
    0.41
     adding
    0.41
     graphing
    0.39
     menambahkan
    0.38
     induction
    0.38
     enhancement
    0.38
     modeling
    0.37
     admitting
    0.37
     ढ
    0.37
    Activations Density 0.001%

    No Known Activations