© 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. 60137
    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
    ۹
    1.06
    어
    1.00
    К
    0.97
    О
    0.91
    ﺄ
    0.89
    Б
    0.87
    시
    0.85
    وی
    0.84
    З
    0.84
     ۸
    0.83
    POSITIVE LOGITS
    2
    0.78
    ن
    0.75
    ments
    0.72
    ীর
    0.70
    ang
    0.70
    ן
    0.67
    ib
    0.65
    ikt
    0.64
    ige
    0.64
    iger
    0.64
    Activations Density 0.000%

    No Known Activations