© 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. 1123
    Prev
    Next
    INDEX
    Explanations

    Canada government topics

    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
    portivo
    0.40
     shelves
    0.38
    (&
    0.38
    ensitivity
    0.38
    helves
    0.36
     alt
    0.36
    Ꮈ
    0.36
     গরম
    0.36
     bookshelves
    0.35
     Stamford
    0.35
    POSITIVE LOGITS
    핵
    0.38
    NON
    0.37
    кор
    0.37
    amyl
    0.36
     Masyarakat
    0.36
    اندا
    0.36
    ξε
    0.35
    PRINC
    0.35
     Меди
    0.35
     NON
    0.35
    Activations Density 0.030%

    No Known Activations