© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25758
    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_10_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
    PHI
    0.50
    向き
    0.49
    然
    0.49
    ↵
    0.49
    アフ
    0.49
    𝟬
    0.47
    ေ့
    0.47
    Pn
    0.46
     excited
    0.45
    Lift
    0.45
    POSITIVE LOGITS
    渑
    0.55
     England
    0.51
    ğin
    0.49
    لە
    0.48
     bip
    0.47
    i
    0.47
     pagine
    0.46
     aort
    0.46
    eh
    0.45
    ంటూ
    0.45
    Activations Density 0.000%

    No Known Activations