© 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. 105814
    Prev
    Next
    INDEX
    Explanations

    connections

    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
    l
    1.64
    ن
    1.45
    n
    1.36
    in
    1.28
    도
    1.21
    ని
    1.16
    க்கு
    1.16
    н
    1.14
    ters
    1.09
    p
    1.08
    POSITIVE LOGITS
    1.16
     belirt
    1.02
     yaklaşık
    1.02
     diferite
    1.00
     deberán
    0.99
     cuando
    0.98
    ；
    0.98
     quais
    0.98
                
    0.97
     gusta
    0.96
    Activations Density 0.005%

    No Known Activations