© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 56416
    Prev
    Next
    INDEX
    Explanations

    sandcastles

    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_11_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
    لت
    0.53
    ط
    0.50
    لي
    0.50
    صال
    0.50
    Bris
    0.50
    且
    0.49
     Knows
    0.49
    част
    0.48
    sberg
    0.48
    Bre
    0.48
    POSITIVE LOGITS
     luckily
    0.71
     gorg
    0.70
    i
    0.66
     frogs
    0.66
     emperor
    0.65
     anillos
    0.65
     any
    0.64
     inequalities
    0.64
     antics
    0.64
     empires
    0.63
    Activations Density 0.003%

    No Known Activations