© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204691
    Prev
    Next
    INDEX
    Explanations

    twin sisters, brothers, circles

    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_6_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
    <unused635>
    0.99
    <unused641>
    0.94
    <unused226>
    0.91
    <unused418>
    0.91
     ευ
    0.90
    ađ
    0.88
    <unused2182>
    0.88
    ação
    0.88
     ayatan
    0.88
    gono
    0.88
    POSITIVE LOGITS
    1
    1.02
     are
    1.01
    ，
    1.01
    ید
    0.98
    ،
    0.97
    t
    0.96
    ।
    0.95
    IS
    0.94
    IN
    0.89
     have
    0.88
    Activations Density 0.005%

    No Known Activations