© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148957
    Prev
    Next
    INDEX
    Explanations

    matrix and vector components

    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_23_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
    絶縁
    0.43
     அவர்கள்
    0.40
    獅
    0.39
    洖
    0.39
    简体
    0.38
    सद
    0.37
     schönsten
    0.37
     odds
    0.36
     prendere
    0.36
     ಹಿಂದ
    0.36
    POSITIVE LOGITS
     ida
    0.40
     rio
    0.39
     otra
    0.39
    LException
    0.38
    Inform
    0.38
    Another
    0.37
    ripple
    0.37
    Ḵ
    0.37
    Pais
    0.37
    ρ
    0.36
    Activations Density 0.001%

    No Known Activations