© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 209670
    Prev
    Next
    INDEX
    Explanations

    context cancellation signals

    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_20_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
     pesar
    0.48
     notifies
    0.47
    }");
    0.43
     instill
    0.43
     berusia
    0.43
     histórico
    0.43
     kingdoms
    0.42
    ionicons
    0.41
     atmosfer
    0.41
    /',
    0.41
    POSITIVE LOGITS
     गोवा
    0.45
     conceptually
    0.42
    SIZE
    0.42
    sequ
    0.41
    ण
    0.41
    हाँ
    0.40
     تحتاج
    0.40
    mii
    0.40
    انيا
    0.39
    thead
    0.39
    Activations Density 0.000%

    No Known Activations