© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193537
    Prev
    Next
    INDEX
    Explanations

    Brits, Britain, BritBox

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_4_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
    ز
    1.03
    ل
    0.98
    or
    0.96
    garden
    0.93
    し
    0.93
    ون
    0.92
    z
    0.92
    ේ
    0.92
    gard
    0.91
    i
    0.91
    POSITIVE LOGITS
    ’
    1.19
    0
    0.93
     contesto
    0.89
     constante
    0.84
    )’
    0.82
     traduc
    0.77
     connecté
    0.75
     доба
    0.74
     criou
    0.73
     était
    0.73
    Activations Density 0.001%

    No Known Activations