© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215215
    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_5_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
    า
    1.21
    3
    1.10
    .
    1.01
    ोदय
    0.94
    ্ড
    0.93
    1
    0.85
    )));
    0.83
    ா
    0.80
    aa
    0.80
    кі
    0.78
    POSITIVE LOGITS
     I
    1.09
    स
    1.02
    íduos
    1.02
    있
    1.02
    ન
    0.98
     anál
    0.96
    د
    0.96
     renormal
    0.96
    자
    0.95
    り
    0.93
    Activations Density 0.000%

    No Known Activations