© 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. 132685
    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
     മറ്റു
    0.39
    form
    0.38
     doom
    0.38
    assadors
    0.37
    orak
    0.37
    ෂ
    0.37
    azure
    0.36
    atorio
    0.36
    Agora
    0.36
    track
    0.35
    POSITIVE LOGITS
     extra
    0.52
    Extra
    0.50
     अतिरिक्त
    0.50
     Extra
    0.49
     ekstra
    0.48
     EXTRA
    0.47
    extra
    0.46
    EXTRA
    0.41
    <unused52>
    0.41
     പതി
    0.40
    Activations Density 0.000%

    No Known Activations