© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42393
    Prev
    Next
    INDEX
    Explanations

    SCG, Johnson, Speed, abank

    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_3_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
     u
    0.66
    กับการ
    0.59
    dır
    0.57
     tomada
    0.56
     manca
    0.55
    ın
    0.55
    ก็
    0.55
     podía
    0.54
     steeple
    0.53
     medis
    0.52
    POSITIVE LOGITS
    할
    0.91
    した
    0.88
    خ
    0.79
    in
    0.75
    ل
    0.71
    ية
    0.70
    天
    0.70
    ة
    0.67
    elijke
    0.66
    Down
    0.65
    Activations Density 0.004%

    No Known Activations