© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160460
    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
    jährige
    0.98
    0
    0.96
    ách
    0.96
    lesque
    0.95
     사람
    0.88
    rances
    0.86
    st
    0.85
    тировать
    0.85
    식회사
    0.85
    ಲಾಯಿತು
    0.84
    POSITIVE LOGITS
    ی
    1.58
    ات
    1.47
    2
    1.46
    AN
    1.43
    RO
    1.42
    ใน
    1.41
    ın
    1.40
    ，
    1.38
    の
    1.38
    ut
    1.36
    Activations Density 0.000%

    No Known Activations