© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133948
    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_1_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
    3
    1.10
    4
    0.98
    (
    0.95
    5
    0.93
     predators
    0.91
     as
    0.91
    ៤
    0.90
    য়ে
    0.88
    8
    0.88
    은
    0.88
    POSITIVE LOGITS
    at
    1.46
    ра
    1.11
    al
    1.06
    soluble
    1.05
    ุ
    1.01
    splitting
    0.98
    tied
    0.98
    f
    0.95
    shuffle
    0.95
    sufficient
    0.94
    Activations Density 0.000%

    No Known Activations