© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207516
    Prev
    Next
    INDEX
    Explanations

    CMYK printing

    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_20_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
    了他的
    0.50
     módulos
    0.46
     Chestnut
    0.44
    ◸
    0.44
     цент
    0.44
     Servicios
    0.44
     Physik
    0.43
    Microelectronics
    0.42
     становништво
    0.42
     bilim
    0.42
    POSITIVE LOGITS
    ong
    0.48
    i
    0.47
     r
    0.44
    onga
    0.44
    歸
    0.44
    iono
    0.43
    r
    0.43
     recall
    0.42
     elected
    0.42
     reward
    0.42
    Activations Density 0.000%

    No Known Activations