© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25379
    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_10_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
    and
    0.54
    9
    0.53
    ９
    0.51
     anew
    0.50
     благоприят
    0.49
    Wer
    0.48
    ابہ
    0.48
    льд
    0.47
    変わ
    0.47
    Tür
    0.47
    POSITIVE LOGITS
    s
    0.49
     لام
    0.49
    ep
    0.48
    خ
    0.48
     ट्रोल
    0.46
     இயக்குனர்
    0.46
     জায়গা
    0.45
    дете
    0.45
     X
    0.45
     टुकड़े
    0.44
    Activations Density 0.000%

    No Known Activations