© 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. 28295
    Prev
    Next
    INDEX
    Explanations

    python code snippets

    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
    IPPING
    0.35
     getMenuInflater
    0.34
     यून
    0.33
     Panels
    0.33
     भव
    0.33
    ございました
    0.33
    ატი
    0.32
    ^{-/-}$
    0.32
     ऋतु
    0.32
    环境下
    0.32
    POSITIVE LOGITS
     apostle
    0.39
     Odd
    0.38
    odd
    0.37
    Odd
    0.37
    崗
    0.36
    መሪያ
    0.36
     Apostle
    0.34
     odd
    0.33
    써
    0.33
    erView
    0.32
    Activations Density 0.010%

    No Known Activations