© 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
    2. Gemma-3-27B-IT
    3. 27-GEMMASCOPE-2-TRANSCODER-262K
    4. 196782
    Prev
    Next
    INDEX
    Explanations

    proposed method or system

    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_27_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
     জুটি
    0.29
    ര്‍ന്ന്
    0.29
     ተመሳሳይ
    0.28
    ﯼ
    0.28
    ಿಸಿದ್ದ
    0.28
    াপুর
    0.27
    ято
    0.27
    ↝
    0.26
     решила
    0.26
    ريبا
    0.26
    POSITIVE LOGITS
     Estimates
    0.29
     Dashboard
    0.28
     Moot
    0.28
     L
    0.27
     Lawn
    0.27
     License
    0.27
     tous
    0.27
     DNS
    0.27
     familles
    0.27
    ")
    0.26
    Activations Density 0.000%

    No Known Activations