© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163642
    Prev
    Next
    INDEX
    Explanations

    em dash for emphasis or setting off clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_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
     headings
    0.44
    headings
    0.38
     Neb
    0.37
    Neb
    0.37
     раздела
    0.37
     Sterne
    0.36
    section
    0.36
    ('#
    0.35
     உடல்
    0.35
     उभर
    0.35
    POSITIVE LOGITS
     squeeze
    0.39
     Packed
    0.38
     packed
    0.38
    Packed
    0.38
    OptionsMenu
    0.37
     revise
    0.36
     gly
    0.36
     बीएससी
    0.36
     Tribes
    0.36
     ballon
    0.36
    Activations Density 0.004%

    No Known Activations