© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201641
    Prev
    Next
    INDEX
    Explanations

    Warren McCulloch, Warren Buffett, Warren Peace, Warren James

    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_12_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
     bungee
    0.54
     spells
    0.51
     $\
    0.50
    دي
    0.48
     digital
    0.47
    र
    0.47
     vehicle
    0.46
     del
    0.46
     X
    0.45
     R
    0.45
    POSITIVE LOGITS
    abria
    0.55
    ución
    0.55
    ம்
    0.54
    uña
    0.53
    ální
    0.49
    стів
    0.49
    っております
    0.49
    ريقيا
    0.48
    桨
    0.48
    aság
    0.48
    Activations Density 0.000%

    No Known Activations