© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5097
    Prev
    Next
    INDEX
    Explanations

    capital city answers

    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_40_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
     Peyton
    0.42
    META
    0.40
     mergeddata
    0.38
    wash
    0.37
     wash
    0.36
     mask
    0.36
     Butler
    0.35
    (()=>{
    0.35
     Tw
    0.35
     Hold
    0.35
    POSITIVE LOGITS
    Activity
    0.42
    CAT
    0.38
    google
    0.38
     ber
    0.37
     Cot
    0.37
     programmatic
    0.37
    isht
    0.37
     CAT
    0.37
     COT
    0.36
    Cot
    0.36
    Activations Density 0.148%

    No Known Activations