© 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. 2797
    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
    știg
    1.86
     estre
    1.77
     rozgry
    1.76
     menem
    1.70
    perature
    1.67
    u
    1.66
    Б
    1.64
     Liet
    1.58
     osim
    1.58
     acumen
    1.58
    POSITIVE LOGITS
    ة
    2.21
    ه
    2.19
    υ
    2.07
     मिलकर
    1.94
    னர்
    1.93
    ங்கிணை
    1.90
    clu
    1.81
    ce
    1.80
    辙
    1.77
    verse
    1.77
    Activations Density 0.125%

    No Known Activations