© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50179
    Prev
    Next
    INDEX
    Explanations

    code closing brace or delimiter

    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_30_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
    Fallback
    0.38
    𝐋
    0.38
    ForgotPassword
    0.36
     отвер
    0.35
    Colleg
    0.34
    >^
    0.34
     Zh
    0.34
    Diameter
    0.33
     militants
    0.33
     Questa
    0.33
    POSITIVE LOGITS
     Glut
    0.41
    tten
    0.39
    enade
    0.37
     രജി
    0.36
     turnt
    0.35
     Regist
    0.34
    搐
    0.33
     estado
    0.33
    饯
    0.33
     filled
    0.32
    Activations Density 0.060%

    No Known Activations