© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175574
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_24_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
     varm
    0.52
    ها
    0.51
     fixed
    0.48
    一つ
    0.48
    固定
    0.47
    هم
    0.46
     insulation
    0.46
    ה
    0.46
     satu
    0.45
     hours
    0.45
    POSITIVE LOGITS
    ividade
    0.58
    rawData
    0.57
    间的
    0.52
     页
    0.52
    ovala
    0.50
    ate
    0.50
    oules
    0.50
    ab
    0.49
    usammen
    0.49
    ък
    0.49
    Activations Density 0.000%

    No Known Activations