© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40659
    Prev
    Next
    INDEX
    Explanations

    student, students

    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_11_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
     Normdatei
    0.57
    ]，
    0.57
     Մ
    0.55
    &)
    0.55
     cosidd
    0.54
    ！)
    0.54
     Hanford
    0.53
    ی
    0.53
    oload
    0.53
    扌
    0.52
    POSITIVE LOGITS
     incidental
    0.56
     laws
    0.55
     bargains
    0.55
     erect
    0.55
     intangible
    0.55
     efectu
    0.54
    дио
    0.54
     shenanigans
    0.53
     pianos
    0.52
    गाय
    0.52
    Activations Density 0.003%

    No Known Activations