© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 196800
    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_4_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
    L
    0.56
    I
    0.51
    Ann
    0.48
    Grupo
    0.48
    A
    0.48
    D
    0.47
    Trust
    0.46
    ডেট
    0.46
    Background
    0.45
    N
    0.45
    POSITIVE LOGITS
    शे
    0.54
     alınd
    0.54
    льну
    0.54
    -->'
    0.49
     ट्रायंगल
    0.48
     букмекерлер
    0.48
    у
    0.48
     protéines
    0.47
    ໆ
    0.47
    є
    0.47
    Activations Density 0.000%

    No Known Activations