© 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. 199814
    Prev
    Next
    INDEX
    Explanations

    German things

    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
    ナン
    0.38
     Rob
    0.37
    flatMap
    0.37
    Cong
    0.36
    Prem
    0.36
     Max
    0.36
    帅
    0.36
    cor
    0.35
     banner
    0.35
    ress
    0.35
    POSITIVE LOGITS
     ਸੰ
    0.41
    UserService
    0.41
     കെ
    0.40
    θεί
    0.36
    oben
    0.35
     typesetting
    0.35
     (--
    0.35
     തന്നെ
    0.35
     sanding
    0.35
     ಕೆ
    0.35
    Activations Density 0.016%

    No Known Activations