© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165492
    Prev
    Next
    INDEX
    Explanations

    drawing and painting graphics

    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_31_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
     financi
    0.41
     expropri
    0.39
     Smol
    0.38
     renegoti
    0.38
    膚
    0.37
     بنائے
    0.37
     голе
    0.37
     Cody
    0.37
     thao
    0.37
    殲
    0.37
    POSITIVE LOGITS
     rotated
    0.47
     rotating
    0.43
    idur
    0.40
    Chart
    0.38
     ligeramente
    0.38
    ViewModels
    0.36
     visualisation
    0.36
    旋转
    0.35
     descans
    0.35
     Calibration
    0.35
    Activations Density 0.001%

    No Known Activations