© 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. 172579
    Prev
    Next
    INDEX
    Explanations

    run away from

    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
    犠
    0.44
    клады
    0.42
     inverses
    0.42
    ドー
    0.42
    対策
    0.41
    rai
    0.40
     অগ্নি
    0.38
     অংশগ্রহণ
    0.38
    ≤
    0.38
    Sites
    0.37
    POSITIVE LOGITS
     kullanılır
    0.51
     Riviera
    0.49
     புதிய
    0.46
     новым
    0.46
     করল
    0.46
     പുതിയ
    0.43
    ameron
    0.43
     allure
    0.42
     mật
    0.42
     வால்பேப்பர்
    0.42
    Activations Density 0.001%

    No Known Activations