© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 197378
    Prev
    Next
    INDEX
    Explanations

    reading donations, running until, adipiscing elit

    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_26_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
     ব্যাকটের
    0.48
     amyloid
    0.48
     ट्रॉपिकल
    0.47
     Ausgabe
    0.46
     británico
    0.46
    <unused338>
    0.46
     moyen
    0.44
     daarbij
    0.44
     नितिन
    0.44
     ferrite
    0.44
    POSITIVE LOGITS
    ান
    0.48
    OS
    0.48
    ts
    0.48
     s
    0.45
    ult
    0.45
    ta
    0.45
    U
    0.45
    ار
    0.45
    HR
    0.44
    。
    0.44
    Activations Density 0.000%

    No Known Activations