© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216458
    Prev
    Next
    INDEX
    Explanations

    I am, I understand, I want

    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_31_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
     généralement
    0.41
    ステー
    0.40
     ಅವರನ್ನು
    0.39
     परन्तु
    0.39
     তাহাদিগকে
    0.38
    センター
    0.38
    詈
    0.38
    悸
    0.37
    却没有
    0.37
    로부터
    0.37
    POSITIVE LOGITS
    Target
    0.42
     Suez
    0.40
     Def
    0.40
    Trust
    0.40
     Liss
    0.37
     targets
    0.37
     Publicity
    0.37
     defensive
    0.37
    Lis
    0.37
     mayoral
    0.37
    Activations Density 0.000%

    No Known Activations