© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59156
    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_2_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
    ي
    1.22
    انية
    1.16
    ك
    1.11
    ле
    1.05
    يته
    0.95
    ارة
    0.91
    كام
    0.91
    ிகள்
    0.89
     تاريخ
    0.89
     Russische
    0.89
    POSITIVE LOGITS
     with
    1.79
     to
    1.60
     from
    1.57
    1
    1.49
     by
    1.48
    ai
    1.40
    8
    1.38
    ES
    1.29
    é
    1.27
    ain
    1.26
    Activations Density 0.000%

    No Known Activations