© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166938
    Prev
    Next
    INDEX
    Explanations

    common areas and spaces

    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_34_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
     редак
    0.47
    regate
    0.41
    萻
    0.38
    ingredients
    0.38
    餐廳
    0.38
    restaurant
    0.37
     adição
    0.36
     зачем
    0.36
    뀜
    0.35
    ítica
    0.35
    POSITIVE LOGITS
     Deng
    0.44
    aniu
    0.40
     nia
    0.40
     Liang
    0.40
     void
    0.40
     acetic
    0.39
    Anh
    0.38
     unprotected
    0.38
     mavi
    0.38
     pes
    0.37
    Activations Density 0.001%

    No Known Activations