© 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. 133106
    Prev
    Next
    INDEX
    Explanations

    Lucy Faithful Foundation

    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
    Santiago
    0.40
     mandated
    0.39
    ϫ
    0.39
     breeze
    0.38
     जयंती
    0.38
    Jay
    0.38
     sandpaper
    0.38
     manip
    0.37
     Santiago
    0.37
    Sandy
    0.37
    POSITIVE LOGITS
    აქ
    0.39
    악
    0.38
    मु
    0.38
    གས་
    0.38
    penas
    0.38
    硫
    0.37
     لہ
    0.37
    hal
    0.37
    elementReference
    0.37
     hipótes
    0.37
    Activations Density 0.001%

    No Known Activations