© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261891
    Prev
    Next
    INDEX
    Explanations

    more than / happier with

    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_22_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
    尼亚
    0.40
     जि
    0.38
    保守
    0.37
     بتر
    0.37
    랍
    0.37
    ્ર
    0.36
     dare
    0.36
     prawo
    0.36
    parent
    0.36
    assignment
    0.36
    POSITIVE LOGITS
     coy
    0.41
     क्विंटल
    0.41
     쭉
    0.41
    wech
    0.41
     organically
    0.40
     പൂർ
    0.38
    юй
    0.38
    ့်
    0.38
     klassischen
    0.38
    섰
    0.38
    Activations Density 0.000%

    No Known Activations