© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 204983
    Prev
    Next
    INDEX
    Explanations

    business roles

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    ,...
    0.37
     papers
    0.32
    ,]
    0.31
    ગ
    0.31
     démar
    0.31
    参赛
    0.31
     easily
    0.30
     ...
    0.30
    править
    0.30
    =["
    0.30
    POSITIVE LOGITS
    懿
    0.41
     delineation
    0.40
    Transitions
    0.39
     page
    0.39
     class
    0.38
    lovers
    0.38
     Dealers
    0.38
     सेटिंग
    0.38
     Transitions
    0.38
    ቃል
    0.38
    Activations Density 0.014%

    No Known Activations