© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 197668
    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_9_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
    anded
    0.66
    ined
    0.57
    able
    0.53
    lag
    0.53
    agn
    0.52
    uster
    0.51
    ñ
    0.51
    we
    0.50
    aya
    0.50
    ip
    0.50
    POSITIVE LOGITS
     COMPENSATION
    0.46
     considéré
    0.45
    కు
    0.45
     Кре
    0.45
     COL
    0.44
    ”:
    0.44
    獲得
    0.43
     Approximation
    0.42
     consid
    0.42
     intercamb
    0.42
    Activations Density 0.000%

    No Known Activations