© 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. 110101
    Prev
    Next
    INDEX
    Explanations

    optimum

    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
    0
    1.37
    ۰
    1.09
    '
    1.05
     pylori
    0.98
    ﺐ
    0.96
    
    0.95
     hundred
    0.93
    :
    0.92
     rotational
    0.91
    isan
    0.88
    POSITIVE LOGITS
    ش
    2.16
    س
    1.67
    t
    1.56
    د
    1.52
    هم
    1.46
    ন
    1.44
    c
    1.43
    ম
    1.43
    ма
    1.42
    на
    1.41
    Activations Density 0.000%

    No Known Activations