© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83427
    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_0_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
    ти
    1.25
    ow
    1.22
    ब्ल्यू
    1.17
    n
    1.16
    𝙚
    1.09
    ή
    1.04
    تی
    1.03
    ashe
    1.03
    𝙖
    1.02
    eer
    1.00
    POSITIVE LOGITS
    ج
    1.73
     in
    1.73
    ل
    1.65
    ال
    1.58
    л
    1.56
    ни
    1.44
    ط
    1.38
    在
    1.38
    ر
    1.35
     در
    1.27
    Activations Density 0.000%

    No Known Activations