© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 90324
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    गुरु
    0.42
     망
    0.42
     कह
    0.42
     Una
    0.40
    संक
    0.39
     如
    0.38
     gate
    0.38
    命运
    0.38
     trin
    0.38
    ラン
    0.37
    POSITIVE LOGITS
    㴓
    0.40
    iteľ
    0.38
     kubwa
    0.38
    pertino
    0.37
    ക്ടര്‍
    0.37
    Traditionally
    0.36
    вався
    0.36
    katkan
    0.36
    티브
    0.36
     সীমান্তে
    0.36
    Activations Density 0.000%

    No Known Activations