© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198672
    Prev
    Next
    INDEX
    Explanations

    say "far"

    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
     Sway
    0.38
    جراء
    0.38
    ጡ
    0.38
    آ
    0.38
    phosphat
    0.36
    كا
    0.36
    setP
    0.36
     своем
    0.36
    গ্রেস
    0.35
    אָ
    0.35
    POSITIVE LOGITS
    боры
    0.39
    ultats
    0.39
     Sage
    0.37
    спеди
    0.37
     Dmitri
    0.36
     sage
    0.36
    getInstalled
    0.36
    羮
    0.35
    韬
    0.35
    umballMachine
    0.35
    Activations Density 0.004%

    No Known Activations