© 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. 3797
    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
     abgesch
    2.02
     ibid
    1.99
    知道
    1.86
     أكتوبر
    1.86
     sheer
    1.85
    로
    1.84
    asjon
    1.84
     pojawi
    1.83
     kanamycin
    1.82
     целях
    1.81
    POSITIVE LOGITS
    нда
    2.17
    ה
    2.01
    fread
    1.99
    mathfrak
    1.97
     exce
    1.89
    ده
    1.86
    ্য
    1.76
    ვ
    1.71
    િક્ષ
    1.69
    ления
    1.69
    Activations Density 0.006%

    No Known Activations