© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 148919
    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_18_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
    ালন
    0.58
    ಿದರೆ
    0.55
    ulloch
    0.53
    洿
    0.50
     nadal
    0.49
     aastal
    0.48
    ظل
    0.47
    aib
    0.47
     pokud
    0.46
    укра
    0.46
    POSITIVE LOGITS
     contains
    0.52
     produces
    0.51
     contiene
    0.51
     implies
    0.50
    '
    0.50
     directs
    0.49
     expresses
    0.48
     describes
    0.48
     authorizes
    0.47
     promotes
    0.47
    Activations Density 0.000%

    No Known Activations