© 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. 648
    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
    !='
    2.71
    vgl
    2.68
    ishly
    2.51
     natively
    2.42
     appunto
    2.38
    い
    2.34
    ⃣
    2.34
    ことを
    2.33
    滸
    2.33
    ]!='
    2.33
    POSITIVE LOGITS
     gens
    2.92
    ્ટ
    2.27
    מה
    2.26
    ele
    2.26
    llen
    2.13
    ole
    2.13
    ev
    2.13
    लों
    2.10
    eness
    2.09
    ்
    2.07
    Activations Density 0.022%

    No Known Activations