© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 219362
    Prev
    Next
    INDEX
    Explanations

    names and brands

    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_47_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
     ArrayIndex
    0.39
    天下
    0.38
     मिल्
    0.38
    THz
    0.37
     eingestellt
    0.37
    ufl
    0.36
    RADIUS
    0.36
    钱
    0.36
     unlaw
    0.36
     বণ
    0.36
    POSITIVE LOGITS
    Or
    0.45
    Ek
    0.42
     ದು
    0.39
     Or
    0.39
     polysaccharide
    0.38
     Ek
    0.38
    ovariant
    0.37
    ede
    0.37
     Louisa
    0.37
    owa
    0.37
    Activations Density 0.000%

    No Known Activations