© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1227
    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
    2.53
    affiliated
    2.48
    cendo
    2.43
    ANEOUS
    2.39
    γ
    2.35
    着用
    2.33
    '.$
    2.32
    гу
    2.29
    IBLE
    2.24
    the
    2.24
    POSITIVE LOGITS
     sorts
    3.01
    તિ
    2.94
    lox
    2.93
     utmost
    2.71
     quede
    2.66
     SizedBox
    2.57
    至于
    2.53
     course
    2.53
    at
    2.52
     sobra
    2.52
    Activations Density 0.573%

    No Known Activations