© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43668
    Prev
    Next
    INDEX
    Explanations

    screenshot evidence

    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_22_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
     차량
    0.37
     butadiene
    0.36
     Wikipédia
    0.35
     अलविदा
    0.35
    량
    0.35
    ঘুম
    0.34
     অটো
    0.34
    飡
    0.34
     hors
    0.34
     Automobiles
    0.34
    POSITIVE LOGITS
     nueva
    0.39
    campus
    0.38
    ULAR
    0.37
    Stamped
    0.37
    𝚇
    0.37
    rences
    0.36
     polygonal
    0.36
     photographing
    0.36
    Nuevo
    0.36
     nuevo
    0.36
    Activations Density 0.002%

    No Known Activations