© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158478
    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_2_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
    ש
    1.58
    ン
    1.48
    ن
    1.48
     importantes
    1.43
    ס
    1.32
     curvas
    1.29
    디
    1.27
     vultures
    1.26
    ஹ
    1.26
     importants
    1.25
    POSITIVE LOGITS
    '
    1.61
    and
    1.49
    pro
    1.45
    ap
    1.34
    af
    1.32
    ig
    1.31
    ad
    1.27
    ick
    1.27
    problem
    1.26
    ip
    1.25
    Activations Density 0.000%

    No Known Activations