© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132055
    Prev
    Next
    INDEX
    Explanations

    writers

    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
    il
    1.23
    ل
    1.10
    j
    1.09
    مان
    1.05
    p
    1.05
    v
    1.05
    к
    1.04
    ัน
    1.03
    ून
    1.02
    т
    1.02
    POSITIVE LOGITS
    𝘆
    1.04
    0
    0.94
    އ
    0.91
    amı
    0.90
    𝘰
    0.89
    OUR
    0.88
    কিছু
    0.86
    ၅
    0.86
    ᱗
    0.86
    phi
    0.84
    Activations Density 0.001%

    No Known Activations