© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3672
    Prev
    Next
    INDEX
    Explanations

    remove off taking off

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    有过
    0.39
    cheek
    0.38
     Kard
    0.37
    ቅ
    0.36
     Clover
    0.35
     Reset
    0.34
    Տ
    0.34
     މި
    0.34
    ంధ
    0.34
    தற்கு
    0.34
    POSITIVE LOGITS
     off
    1.09
    off
    0.93
    Off
    0.83
    オフ
    0.79
     Off
    0.79
     offs
    0.76
     OFF
    0.75
     removing
    0.67
     removed
    0.65
     removal
    0.63
    Activations Density 0.126%

    No Known Activations