© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24139
    Prev
    Next
    INDEX
    Explanations

    recent open

    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_10_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
     evaluar
    0.47
    ник
    0.47
     affidavits
    0.46
     asumir
    0.46
    ᓲ
    0.46
     altres
    0.46
     Affordable
    0.45
     exclusions
    0.45
     erreur
    0.45
     unwa
    0.45
    POSITIVE LOGITS
    or
    0.69
    ome
    0.63
    oc
    0.59
    of
    0.57
    Red
    0.56
    ou
    0.56
    produ
    0.55
    wood
    0.55
    n
    0.54
    read
    0.54
    Activations Density 0.000%

    No Known Activations