© 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. 130121
    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
    chad
    0.43
    hd
    0.40
     eint
    0.40
    苹
    0.40
    papier
    0.39
    ад
    0.38
    㠃
    0.37
    閆
    0.37
    appt
    0.36
    ocial
    0.36
    POSITIVE LOGITS
     colocar
    0.39
     ছুর
    0.36
    লীর
    0.36
    ❍
    0.35
    انة
    0.34
    ская
    0.34
    ската
    0.34
     terbatas
    0.34
    ᑐ
    0.34
     Suz
    0.33
    Activations Density 0.000%

    No Known Activations