© 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. 1392
    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
    ب
    3.02
    м
    2.74
    𝘮
    2.56
    ie
    2.55
    ك
    2.51
    órios
    2.28
     ゙
    2.26
    ot
    2.26
    capable
    2.26
    on
    2.21
    POSITIVE LOGITS
    reason
    2.15
     питания
    2.08
    朹
    2.08
     zaradi
    2.08
     Benutzer
    2.03
    ların
    2.03
    quisites
    2.03
     annat
    1.97
    ní
    1.97
    ricks
    1.95
    Activations Density 0.037%

    No Known Activations