© 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. 2417
    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
    mis
    1.03
    at
    0.98
    le
    0.91
    erne
    0.89
    야
    0.87
    er
    0.85
    kau
    0.82
    度
    0.82
    lemente
    0.82
    ു
    0.82
    POSITIVE LOGITS
    يه
    1.24
    Ş
    1.01
     ця
    1.00
     dissipated
    0.98
     endeavour
    0.95
    groupby
    0.94
    怸
    0.93
    Surviv
    0.93
    antiated
    0.93
     displeasure
    0.91
    Activations Density 0.024%

    No Known Activations