© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164028
    Prev
    Next
    INDEX
    Explanations

    you for asking

    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_31_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
    었어요
    0.39
     परन्तु
    0.36
     Noh
    0.35
     clásica
    0.34
    marquee
    0.34
    
    0.34
    modular
    0.33
     முற
    0.33
     típico
    0.33
    wsdl
    0.33
    POSITIVE LOGITS
     പിന്തുണ
    0.47
     support
    0.45
     bravely
    0.43
     싶은
    0.43
     posti
    0.41
     поддержку
    0.40
     dukungan
    0.39
    婊
    0.39
     prava
    0.39
     suporte
    0.38
    Activations Density 0.001%

    No Known Activations