© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29724
    Prev
    Next
    INDEX
    Explanations

    yellow

    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_10_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
    plain
    0.21
    geon
    0.21
    τει
    0.20
    calar
    0.20
    लिन
    0.20
    髏
    0.19
    сив
    0.19
    tey
    0.19
    nton
    0.19
    bley
    0.19
    POSITIVE LOGITS
     hör
    0.21
     desejo
    0.20
     lanz
    0.19
    や
    0.19
     wyk
    0.19
     on
    0.19
     that
    0.19
    指示
    0.19
     zdravot
    0.19
     Cependant
    0.19
    Activations Density 0.026%

    No Known Activations