© 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. 132376
    Prev
    Next
    INDEX
    Explanations

    store

    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
     الكريم
    1.02
    고
    1.00
    𝙜
    0.90
    지
    0.89
    كان
    0.87
    大
    0.86
    𝙩
    0.86
    ቂያ
    0.86
    дно
    0.85
    ća
    0.82
    POSITIVE LOGITS
    ol
    1.28
    ing
    1.22
    i
    1.21
    ic
    1.11
    k
    1.11
    ed
    1.06
    y
    1.03
     b
    1.02
    ine
    1.02
    in
    1.00
    Activations Density 0.001%

    No Known Activations