© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 593
    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
    з
    2.99
    mention
    2.77
    %>%
    2.76
     fluidized
    2.75
    deki
    2.66
    tır
    2.60
     nltk
    2.60
    orderby
    2.55
    t
    2.53
    dives
    2.52
    POSITIVE LOGITS
     been
    5.59
     varit
    3.80
    been
    3.78
    Been
    3.70
     sido
    3.52
     været
    3.35
     vært
    3.26
     BEEN
    3.26
     got
    3.12
     Been
    2.98
    Activations Density 0.241%

    No Known Activations