© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 88820
    Prev
    Next
    INDEX
    Explanations

    and conjunc, font, Edison

    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
     of
    1.13
    지
    1.02
    ות
    1.00
    트
    0.92
    었
    0.87
    ات
    0.86
    म
    0.86
    지에
    0.85
    ation
    0.81
    תו
    0.80
    POSITIVE LOGITS
    and
    0.75
    ᅬ
    0.68
    Shivam
    0.68
    мени
    0.66
    Vt
    0.65
    I
    0.64
    ip
    0.63
    SM
    0.63
    {
    0.62
    Bài
    0.61
    Activations Density 0.020%

    No Known Activations