© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8655
    Prev
    Next
    INDEX
    Explanations

    BMW

    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_13_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
     ਤ
    0.27
     мо
    0.27
     தம்
    0.26
    quête
    0.26
    ﮄ
    0.25
     टूर्
    0.25
     ભાગ
    0.25
     uncomplicated
    0.25
     нама
    0.25
     relinquished
    0.25
    POSITIVE LOGITS
    (^^
    0.33
    Phone
    0.32
    Say
    0.31
    kat
    0.29
    Sorry
    0.29
    Applications
    0.29
    October
    0.29
    Vill
    0.29
    OS
    0.29
    .;
    0.29
    Activations Density 0.000%

    No Known Activations