© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216759
    Prev
    Next
    INDEX
    Explanations

    product features

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     moy
    0.40
     ско
    0.40
    enity
    0.40
     К
    0.40
     kam
    0.39
    kirk
    0.38
     scape
    0.38
    šení
    0.37
     hoofdst
    0.36
    льності
    0.36
    POSITIVE LOGITS
    रि
    0.46
    ராட்ச
    0.40
     Gain
    0.39
     Oj
    0.38
    Accelerometer
    0.38
    रिक
    0.37
    䙲
    0.37
     அரசா
    0.37
    Oj
    0.36
    وتي
    0.36
    Activations Density 0.000%

    No Known Activations