© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32429
    Prev
    Next
    INDEX
    Explanations

    common typos followed by context

    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_7_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
     (
    0.63
     été
    0.52
     μετά
    0.52
    7
    0.51
     heißt
    0.50
     пры
    0.49
    he
    0.49
     он
    0.48
     вас
    0.48
     étant
    0.48
    POSITIVE LOGITS
    ي
    0.55
    ج
    0.50
    ب
    0.50
     pedals
    0.50
    0.49
     langfrist
    0.49
     powertrain
    0.48
    ى
    0.48
     easements
    0.47
     in
    0.46
    Activations Density 0.002%

    No Known Activations