© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159563
    Prev
    Next
    INDEX
    Explanations

    up the

    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_2_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
    ض
    1.02
    ta
    0.96
    in
    0.92
    IN
    0.88
    ↵↵
    0.85
    с
    0.84
    I
    0.84
    ting
    0.83
    าย
    0.83
     केलेले
    0.83
    POSITIVE LOGITS
    ي
    1.47
    ಾ
    1.17
    ل
    1.14
    婼
    1.10
    рама
    1.09
     of
    1.08
    ۳
    1.07
    ۹
    1.05
     egip
    1.02
    ۲
    1.02
    Activations Density 0.003%

    No Known Activations