© 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. 35487
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     कौशल
    0.39
    त्तों
    0.38
    癮
    0.37
    ください
    0.37
     punishable
    0.37
    ılmaz
    0.36
     दुःख
    0.36
    pR
    0.35
     gegeven
    0.35
     draggable
    0.35
    POSITIVE LOGITS
     invincible
    0.42
    χ
    0.41
    aper
    0.38
     infallible
    0.37
    APER
    0.36
     invariably
    0.35
    Bucket
    0.35
    uli
    0.35
    Undefined
    0.34
     కని
    0.33
    Activations Density 0.000%

    No Known Activations