© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27695
    Prev
    Next
    INDEX
    Explanations

    substitutable for their base

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    submenu
    0.46
    ulk
    0.38
    wright
    0.38
     Prism
    0.37
    right
    0.37
    ссер
    0.36
    兼
    0.36
     CCA
    0.36
    shaft
    0.36
    光滑
    0.36
    POSITIVE LOGITS
     pollute
    0.40
     polity
    0.39
     polluting
    0.39
    stractions
    0.38
     फ्लाई
    0.38
    沌
    0.38
     Valeria
    0.37
     روا
    0.36
    郎
    0.36
    ចាយ
    0.36
    Activations Density 0.000%

    No Known Activations