© 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. 1156
    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
    tion
    3.17
    ted
    2.98
    tor
    2.69
    taining
    2.44
    temp
    2.30
    t
    2.29
    tar
    2.27
    ્સ
    2.26
    ्स
    2.25
    town
    2.18
    POSITIVE LOGITS
    ibility
    2.44
    ্রো
    2.22
    wanie
    2.22
     seja
    2.06
    દય
    1.99
    ensical
    1.98
     jedoch
    1.96
    针
    1.95
    これが
    1.94
     siquiera
    1.94
    Activations Density 0.163%

    No Known Activations