© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26225
    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
    accompan
    0.60
    岡山
    0.55
    АСС
    0.52
     accompaniment
    0.52
    рыя
    0.51
    ၺ
    0.51
     accompan
    0.50
     množ
    0.49
     playerCount
    0.49
     guia
    0.48
    POSITIVE LOGITS
    are
    0.50
    ika
    0.48
    ۰
    0.48
    than
    0.45
     विवेक
    0.44
    istor
    0.43
    -
    0.42
    ani
    0.42
    oble
    0.42
    il
    0.41
    Activations Density 0.000%

    No Known Activations