© 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. 61749
    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
    ล
    1.83
    ด
    1.68
    י
    1.45
    री
    1.30
    sa
    1.22
    ट
    1.21
    la
    1.19
    ลอง
    1.19
    ו
    1.19
    li
    1.17
    POSITIVE LOGITS
    ма
    1.53
    ية
    1.41
    ся
    1.23
    к
    1.21
    c
    1.17
    کنند
    1.16
    ви
    1.12
    у
    1.12
    ő
    1.11
    kan
    1.09
    Activations Density 0.000%

    No Known Activations