© 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. 42019
    Prev
    Next
    INDEX
    Explanations

    code structure words

    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
    //!
    0.42
    ➲
    0.37
    gas
    0.36
     mencionar
    0.36
    क्षिप्त
    0.36
    </th>
    0.36
    逭
    0.35
                             
    0.34
     podendo
    0.34
     Ihnen
    0.33
    POSITIVE LOGITS
     bribes
    0.39
    केक
    0.38
    על
    0.38
    በር
    0.38
    ปฏิ
    0.37
     جائز
    0.36
    ರೋ
    0.35
    嬗
    0.35
     χρόνια
    0.35
     সেল
    0.35
    Activations Density 0.001%

    No Known Activations