© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5464
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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_44_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
    एएस
    0.41
    perms
    0.37
    Scape
    0.36
    黎
    0.36
    Error
    0.35
    Deb
    0.35
    Greg
    0.35
    Nap
    0.35
    ᄁ
    0.35
    clerc
    0.35
    POSITIVE LOGITS
    🅾
    0.45
     Carlos
    0.39
     carlos
    0.38
     Xt
    0.38
     لوبو
    0.38
    क्षे
    0.37
     engl
    0.37
    욬
    0.37
     юм
    0.37
     wo
    0.37
    Activations Density 0.020%

    No Known Activations