© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21151
    Prev
    Next
    INDEX
    Explanations

    say toggle

    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_56_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
     togg
    0.99
     toggle
    0.98
    Toggle
    0.95
     Toggle
    0.93
    toggle
    0.84
    空
    0.61
    接
    0.52
    CompoundButton
    0.50
    静
    0.50
    掉
    0.50
    POSITIVE LOGITS
    OGLE
    0.73
     토
    0.72
    ogg
    0.68
     T
    0.63
     Т
    0.63
    og
    0.62
    گل
    0.61
     टॉ
    0.61
    גל
    0.61
    oggled
    0.61
    Activations Density 0.022%

    No Known Activations