© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46229
    Prev
    Next
    INDEX
    Explanations

    log/ paths

    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
     त्रास
    0.49
    volve
    0.48
    ligne
    0.48
    seater
    0.46
     freezing
    0.45
    3
    0.44
    stilling
    0.44
    ウンド
    0.44
    atural
    0.43
     yüzy
    0.43
    POSITIVE LOGITS
    툐
    0.46
     lij
    0.46
     académicos
    0.45
     tights
    0.45
     /
    0.42
    <0x0E>
    0.41
    不去
    0.41
    َق
    0.41
     десять
    0.41
     únicamente
    0.41
    Activations Density 0.000%

    No Known Activations