© 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. 40430
    Prev
    Next
    INDEX
    Explanations

    cannons, gunpowder, iron, Islamic Sultan

    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
    :
    0.65
    ans
    0.56
    is
    0.52
    ts
    0.52
    lim
    0.51
    \_
    0.51
    ppermint
    0.50
    :\
    0.50
    iset
    0.50
     međ
    0.50
    POSITIVE LOGITS
     ploch
    0.57
    OD
    0.55
    פא
    0.55
     style
    0.54
     modell
    0.54
     blend
    0.53
     nField
    0.53
    Herkese
    0.52
     mix
    0.52
    HI
    0.52
    Activations Density 0.009%

    No Known Activations