© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 202498
    Prev
    Next
    INDEX
    Explanations

    Search Engine Optimization

    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
    ו
    1.12
    خ
    1.05
    ف
    1.03
    can
    1.00
    for
    0.97
    to
    0.96
    ために
    0.95
    Μ
    0.92
     can
    0.90
    هم
    0.89
    POSITIVE LOGITS
     as
    1.05
    روں
    0.98
    ة
    0.93
    _
    0.90
    வை
    0.87
    z
    0.80
    вання
    0.79
    цю
    0.75
    вати
    0.74
    il
    0.73
    Activations Density 0.003%

    No Known Activations