© 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. 122667
    Prev
    Next
    INDEX
    Explanations

    scenic beauty

    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
    د
    0.79
    ні
    0.77
    نيا
    0.68
    ם
    0.67
    ني
    0.66
    י
    0.64
     buz
    0.64
     predictably
    0.64
     Bél
    0.63
    ન
    0.63
    POSITIVE LOGITS
    t
    1.11
    al
    1.05
    ten
    0.95
    g
    0.91
    to
    0.83
    tr
    0.82
    ant
    0.79
    ty
    0.79
    tion
    0.77
    th
    0.77
    Activations Density 0.000%

    No Known Activations