© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35828
    Prev
    Next
    INDEX
    Explanations

    License verification and places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Rico
    0.43
     commen
    0.41
    िकांना
    0.40
    itato
    0.37
    涣
    0.37
    licken
    0.37
     মুজিবর
    0.37
    ске
    0.37
     शुक्
    0.37
    紬
    0.37
    POSITIVE LOGITS
     L
    0.44
     Bill
    0.41
    yap
    0.40
     Budd
    0.40
     West
    0.39
     Russell
    0.39
     courts
    0.38
     ag
    0.38
    जि
    0.38
     bent
    0.38
    Activations Density 0.014%

    No Known Activations