© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 151377
    Prev
    Next
    INDEX
    Explanations

    look or search for

    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_23_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
     сани
    0.45
     соору
    0.42
    Ὀ
    0.42
     쪽
    0.41
     우리의
    0.41
    :%
    0.40
     సంద
    0.40
    
    0.40
    ⛰
    0.40
     autorités
    0.39
    POSITIVE LOGITS
    连续
    0.42
    ffle
    0.42
     Equilib
    0.41
     equilib
    0.41
    arjo
    0.41
    ক্র
    0.40
     ഇഷ്ട
    0.39
    چین
    0.39
     Machinist
    0.38
    連續
    0.38
    Activations Density 0.001%

    No Known Activations