© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5178
    Prev
    Next
    INDEX
    Explanations

    Practice

    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_44_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
    ovac
    0.44
    流畅
    0.38
     Nine
    0.37
    endela
    0.37
     पीले
    0.37
     낙
    0.37
    ovo
    0.37
     Figs
    0.37
     여섯
    0.37
     ϕ
    0.36
    POSITIVE LOGITS
     Practice
    0.39
     hom
    0.39
     practice
    0.39
     mole
    0.38
     CPR
    0.37
     DCP
    0.37
    Practice
    0.37
     Mommy
    0.37
     Gang
    0.37
     Garn
    0.35
    Activations Density 0.004%

    No Known Activations