© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 94202
    Prev
    Next
    INDEX
    Explanations

    HTML list item closing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    <strong>
    0.50
    ---’
    0.47
    𝒂
    0.45
    ógł
    0.43
    هههه
    0.42
     furono
    0.42
    <span>
    0.41
    :<
    0.41
     incontr
    0.41
    <end_of_turn>
    0.40
    POSITIVE LOGITS
    ("");
    0.52
     "";
    0.50
     "
    0.48
    ("
    0.46
     x
    0.46
     ();
    0.45
    Graphic
    0.44
    ();
    0.43
     Java
    0.43
     X
    0.43
    Activations Density 0.002%

    No Known Activations