© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134872
    Prev
    Next
    INDEX
    Explanations

    Caritas Sweden, Catholic News Agency

    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_6_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
    r
    0.95
    ри
    0.84
    ilin
    0.81
    asing
    0.79
    '
    0.79
    v
    0.79
    igated
    0.77
    к
    0.77
    ucus
    0.75
    anso
    0.75
    POSITIVE LOGITS
    0
    1.46
    2
    0.88
    ；
    0.88
     katol
    0.79
    ๐
    0.76
    நபியே
    0.74
     tän
    0.74
     në
    0.73
     nóng
    0.73
    Incoming
    0.73
    Activations Density 0.000%

    No Known Activations