© 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. 39604
    Prev
    Next
    INDEX
    Explanations

    tells you how

    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
     frayed
    0.59
    ようになりました
    0.57
    ](#
    0.56
     archetype
    0.56
    Fiber
    0.54
     fiber
    0.53
     de
    0.52
     Crav
    0.51
     wrinkle
    0.50
     flared
    0.50
    POSITIVE LOGITS
    n
    0.77
    ↵
    0.70
    7
    0.68
    enfance
    0.65
    ल्
    0.64
    6
    0.63
    améli
    0.62
    ю
    0.61
    lients
    0.60
    ż
    0.60
    Activations Density 0.005%

    No Known Activations