© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26802
    Prev
    Next
    INDEX
    Explanations

    dilution

    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_10_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
    h
    0.54
     ungew
    0.43
     tenter
    0.41
     fortaleza
    0.40
    igated
    0.40
    ни
    0.39
     الدول
    0.39
     pouls
    0.39
     Hadoop
    0.38
     deutschen
    0.38
    POSITIVE LOGITS
    し
    0.53
    '
    0.50
    IT
    0.49
    ED
    0.49
    MC
    0.46
    US
    0.44
    다
    0.44
    의
    0.44
    EM
    0.42
    INK
    0.41
    Activations Density 0.004%

    No Known Activations