© 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. 31823
    Prev
    Next
    INDEX
    Explanations

    it

    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
     faci
    0.35
     centra
    0.34
    QtWidgets
    0.34
     null
    0.34
     vinos
    0.34
    伺
    0.34
     wicht
    0.34
     Česk
    0.34
    ツ
    0.34
     peti
    0.34
    POSITIVE LOGITS
    的很
    0.38
     Kati
    0.37
    是很
    0.36
    itatively
    0.36
     Règles
    0.36
    ವುದು
    0.35
    得很
    0.35
     நல்லது
    0.35
    entially
    0.34
    渉
    0.34
    Activations Density 0.020%

    No Known Activations