© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 131917
    Prev
    Next
    INDEX
    Explanations

    capacity and ability

    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_1_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
    ة
    1.93
    ات
    1.49
    ే
    1.36
    ת
    1.30
    at
    1.29
    ed
    1.22
    ির
    1.13
    ing
    1.12
    ী
    1.12
    ين
    1.09
    POSITIVE LOGITS
    1.03
    ny
    0.89
    net
    0.86
     it
    0.85
    R
    0.84
    ELL
    0.84
    Про
    0.82
     \
    0.80
    Nh
    0.79
    ಬ
    0.79
    Activations Density 0.003%

    No Known Activations