© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91197
    Prev
    Next
    INDEX
    Explanations

    sample or test preparation

    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
    ifra
    0.49
     그림
    0.47
     Hintergrund
    0.46
    樁
    0.46
     esempi
    0.46
    .]:
    0.46
     특별
    0.45
    Storia
    0.45
     ಹೃದಯ
    0.45
     aiuto
    0.45
    POSITIVE LOGITS
     pinched
    0.47
     pourront
    0.46
     softened
    0.45
     burdensome
    0.45
                       
    0.44
    وت
    0.44
    ต์
    0.43
    Мо
    0.43
    وط
    0.43
    Х
    0.42
    Activations Density 0.039%

    No Known Activations