© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 102467
    Prev
    Next
    INDEX
    Explanations

    numbers and financial data

    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_14_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
    Мы
    0.49
    نمية
    0.48
    வ்வேறு
    0.47
    Ра
    0.47
    अच्छ
    0.46
    ानि
    0.45
    ਜ
    0.45
    Во
    0.45
     Democr
    0.42
    我们
    0.41
    POSITIVE LOGITS
    hran
    0.48
    hout
    0.48
     dosing
    0.45
     delay
    0.45
     housing
    0.43
    haus
    0.43
    engl
    0.43
     under
    0.42
     could
    0.42
     بدون
    0.42
    Activations Density 0.006%

    No Known Activations