© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89091
    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_23_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
     অতঃ
    0.41
    केंद्र
    0.40
     अगस्त
    0.39
    veyor
    0.39
    ᐢ
    0.39
     Derry
    0.39
    䐝
    0.39
    𝘫
    0.38
     Neuros
    0.38
    ᵏ
    0.38
    POSITIVE LOGITS
     تقدم
    0.41
     билет
    0.39
    تقدم
    0.37
    inging
    0.37
     هناك
    0.37
     труб
    0.37
    serializing
    0.37
     อื่น
    0.36
     quede
    0.36
     உர
    0.36
    Activations Density 0.000%

    No Known Activations