© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106837
    Prev
    Next
    INDEX
    Explanations

    pea

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    a
    1.27
    ne
    1.23
    b
    1.23
    ați
    1.15
    um
    1.10
    k
    1.04
    но
    1.02
    editing
    1.02
    ką
    0.99
    2
    0.99
    POSITIVE LOGITS
     to
    1.25
    ﺕ
    1.00
     Ци
    0.99
     it
    0.96
     rys
    0.96
     teaspoons
    0.89
     malicious
    0.88
     protect
    0.88
     interpol
    0.88
     ruk
    0.86
    Activations Density 0.001%

    No Known Activations