© 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. 178511
    Prev
    Next
    INDEX
    Explanations

    Unit

    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
    ‟
    0.39
    दी
    0.38
    maa
    0.37
    igns
    0.36
    ensible
    0.36
    ig
    0.36
    Hoy
    0.35
    addle
    0.35
    aben
    0.35
    amat
    0.34
    POSITIVE LOGITS
     ממש
    0.46
     fale
    0.44
     astron
    0.42
     purses
    0.42
    '){$
    0.40
     тестирование
    0.39
     Potatoes
    0.39
     punte
    0.38
     Animation
    0.38
     Astro
    0.38
    Activations Density 0.001%

    No Known Activations