© 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. 154591
    Prev
    Next
    INDEX
    Explanations

    bbc news links

    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_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
    🍖
    0.37
    ँच
    0.37
     compre
    0.34
     unsuccessfully
    0.34
    בוד
    0.34
     survivors
    0.33
    옴
    0.33
     erroneously
    0.33
     perjury
    0.33
     فين
    0.33
    POSITIVE LOGITS
     kiwi
    0.43
    ｎ
    0.43
     Port
    0.42
     Kiwi
    0.42
    illiant
    0.40
    /√
    0.40
    kiwa
    0.39
    ki
    0.39
     pooch
    0.39
     montrent
    0.38
    Activations Density 0.000%

    No Known Activations