© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216194
    Prev
    Next
    INDEX
    Explanations

    Fin

    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دور
    0.44
     kim
    0.44
    ikan
    0.42
     ஈடுப
    0.42
     Kim
    0.41
    Kim
    0.41
    IKV
    0.40
    김
    0.39
    erv
    0.38
    kim
    0.38
    POSITIVE LOGITS
     Guadalupe
    0.43
     selectedCard
    0.43
     Justine
    0.39
    泓
    0.36
    नावली
    0.36
    ួល
    0.36
    腓
    0.36
     grave
    0.36
    ዶች
    0.35
     Guad
    0.35
    Activations Density 0.001%

    No Known Activations