© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214542
    Prev
    Next
    INDEX
    Explanations

    showing how data or content is presented

    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_5_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
    Y
    1.21
    .
    1.19
     as
    1.18
     b
    1.17
     with
    1.16
    רו
    1.11
     be
    1.10
    1
    1.07
     =
    1.06
     by
    1.05
    POSITIVE LOGITS
    म
    1.38
    ни
    1.38
     Antennes
    1.30
    gène
    1.27
     appelez
    1.26
    ના
    1.23
    시
    1.22
    시스템
    1.21
    imam
    1.21
    нага
    1.20
    Activations Density 0.008%

    No Known Activations