© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132576
    Prev
    Next
    INDEX
    Explanations

    in prefixes

    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_1_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
    s
    1.33
    al
    1.07
    text
    1.05
    3
    1.05
    4
    1.03
    ุ
    0.96
    pl
    0.95
    part
    0.95
    toire
    0.95
    ਆਂ
    0.94
    POSITIVE LOGITS
    것
    1.34
    때
    1.16
    нку
    1.01
    не
    0.96
    า
    0.93
    용
    0.90
    럼
    0.90
    ну
    0.89
     поможет
    0.89
    곳
    0.88
    Activations Density 0.000%

    No Known Activations