© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199932
    Prev
    Next
    INDEX
    Explanations

    S shape, turns, direct routes

    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_12_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
     Вели
    0.64
    ja
    0.63
    ili
    0.62
    ala
    0.59
    ě
    0.59
     Бы
    0.57
    ми
    0.57
    ys
    0.56
    ér
    0.56
    ars
    0.55
    POSITIVE LOGITS
    his
    0.61
        
    0.59
    잘
    0.58
    usingCamera
    0.57
     his
    0.55
    이다
    0.53
     differentiable
    0.52
     koleg
    0.52
    간
    0.50
     sillon
    0.49
    Activations Density 0.000%

    No Known Activations