© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 39515
    Prev
    Next
    INDEX
    Explanations

    end of calculation questions

    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_11_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
    نی
    0.33
    ，
    0.33
    他们
    0.32
    ном
    0.30
    り
    0.30
    ме
    0.29
    י
    0.29
    在
    0.29
    ม
    0.28
    ران
    0.28
    POSITIVE LOGITS
    wc
    0.27
    whether
    0.26
    ötz
    0.25
    ic
    0.25
     soweit
    0.24
    pak
    0.24
     genoeg
    0.24
     बेस्ट
    0.24
    ug
    0.23
    uje
    0.23
    Activations Density 0.001%

    No Known Activations