© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 63542
    Prev
    Next
    INDEX
    Explanations

    .

    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_46_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
    垻
    0.40
     transpar
    0.37
    met
    0.37
     linh
    0.37
     proton
    0.36
     pesos
    0.36
     metastases
    0.36
    เช
    0.36
     organizz
    0.36
    हीर
    0.35
    POSITIVE LOGITS
     সিম
    0.37
     छठी
    0.36
     Canning
    0.36
    startup
    0.35
     Experiences
    0.35
    ඃ
    0.35
    ario
    0.34
    啶
    0.34
    𝐰
    0.34
    𝒚
    0.33
    Activations Density 0.000%

    No Known Activations