© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 88677
    Prev
    Next
    INDEX
    Explanations

    function parameters or variables

    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_23_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
     bajas
    0.39
     κά
    0.39
     squadra
    0.38
     تمارين
    0.38
    Quad
    0.38
     fehl
    0.38
     gioi
    0.37
    🆁
    0.37
     inför
    0.37
     ern
    0.36
    POSITIVE LOGITS
    imit
    0.44
    rew
    0.44
    sizing
    0.42
    nios
    0.42
    bordered
    0.41
    skinned
    0.40
    icl
    0.39
    ıt
    0.39
    wrote
    0.39
    ointe
    0.38
    Activations Density 0.003%

    No Known Activations