© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 108450
    Prev
    Next
    INDEX
    Explanations

    Al followed by diverse suffixes

    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
    1
    1.34
    p
    1.06
    g
    1.05
    h
    0.98
    ágina
    0.91
    น่า
    0.91
    r
    0.90
    navigation
    0.85
    heatmap
    0.84
    il
    0.83
    POSITIVE LOGITS
     in
    1.64
     في
    1.27
    ی
    1.27
    도
    1.23
                
    1.22
    ,
    1.22
    も
    1.22
    ન
    1.19
     études
    1.15
    在
    1.15
    Activations Density 0.004%

    No Known Activations