© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158074
    Prev
    Next
    INDEX
    Explanations

    Ja!

    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_2_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
    t
    1.08
    ছে
    1.04
    i
    1.02
    לי
    1.00
     I
    0.96
    o
    0.93
    ៣
    0.91
    ្រ
    0.90
     provoz
    0.90
    য়া
    0.89
    POSITIVE LOGITS
    س
    1.27
    на
    1.23
    า
    0.98
    '
    0.95
    E
    0.91
    स
    0.90
    R
    0.88
    ан
    0.86
    νης
    0.82
    ↵↵
    0.81
    Activations Density 0.003%

    No Known Activations