© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2480
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    er
    2.67
    い
    2.30
    ю
    2.29
    一个
    2.24
    l
    2.20
    り
    2.07
    การ
    2.01
     formatDate
    2.01
    рная
    1.95
    ρθ
    1.94
    POSITIVE LOGITS
    ور
    2.26
    y
    2.07
     negeri
    1.98
    
    1.91
     logits
    1.91
    guas
    1.90
     charmed
    1.84
    keeping
    1.84
     mistaken
    1.84
     уж
    1.81
    Activations Density 0.042%

    No Known Activations