© 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. 195144
    Prev
    Next
    INDEX
    Explanations

    year

    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
     keepers
    0.44
    ष्‍ट्र
    0.37
     مصرف
    0.36
     Chick
    0.36
    كال
    0.35
     Riccardo
    0.35
    esters
    0.35
    獻
    0.35
    keepers
    0.34
     Aside
    0.34
    POSITIVE LOGITS
    EO
    0.46
     guaranteed
    0.46
    onucle
    0.44
     EO
    0.44
     Guaranteed
    0.44
    🧞
    0.41
     tujuh
    0.40
     garant
    0.39
     гаран
    0.39
    вости
    0.39
    Activations Density 0.002%

    No Known Activations