© 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. 51079
    Prev
    Next
    INDEX
    Explanations

    fresh care, carousel, objections, aristocrats

    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
    år
    0.47
    FS
    0.46
     말
    0.45
     منظور
    0.45
    다
    0.45
    phys
    0.44
    SNL
    0.44
    太郎
    0.44
    DO
    0.43
     نه
    0.42
    POSITIVE LOGITS
     Survive
    0.51
     condivid
    0.50
     carelessly
    0.49
     Tories
    0.49
     legalization
    0.48
    ;,
    0.47
     freshmen
    0.47
     communists
    0.47
     Acuerdo
    0.46
    मारा
    0.46
    Activations Density 0.000%

    No Known Activations