© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207738
    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_20_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
    <0x0D>
    0.54
    _
    0.44
     तपाई
    0.43
     anda
    0.41
    }}$.
    0.40
    sm
    0.40
    方的
    0.39
     n
    0.38
     Dawn
    0.38
     Audubon
    0.38
    POSITIVE LOGITS
     glycerol
    0.47
     medan
    0.47
     situatie
    0.46
    Cuál
    0.46
     kondisi
    0.45
     Avrupa
    0.44
    äk
    0.43
     పరిస్థ
    0.43
    HCR
    0.43
     زاويه
    0.43
    Activations Density 0.000%

    No Known Activations