© 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. 216273
    Prev
    Next
    INDEX
    Explanations

    but are / but 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
     Dutta
    0.40
    dogan
    0.39
     신
    0.38
     ముఖ్య
    0.38
    ジナ
    0.38
    mainly
    0.38
     Mohan
    0.38
    爣
    0.37
    寤
    0.37
    გან
    0.36
    POSITIVE LOGITS
     pero
    0.61
     but
    0.55
    이지만
    0.51
    했지만
    0.51
     אבל
    0.50
     लेकिन
    0.50
     لكن
    0.50
     ஆனால்
    0.50
     mutta
    0.47
     nhưng
    0.46
    Activations Density 0.004%

    No Known Activations