© 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. 3193
    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
    де
    2.27
    o
    2.17
    𝐯
    2.10
    ம்
    2.07
    ड
    1.99
    ણી
    1.98
    𝐝
    1.98
    ے
    1.98
    ণ
    1.95
    й
    1.93
    POSITIVE LOGITS
    soever
    2.27
    こちらの
    2.06
     שלא
    2.02
    fullscreen
    1.99
    saw
    1.97
    pence
    1.97
     непло
    1.96
    setUsername
    1.95
    '\
    1.95
    剂
    1.90
    Activations Density 0.039%

    No Known Activations