© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 175883
    Prev
    Next
    INDEX
    Explanations

    formatting wrappers like ** ## --

    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_24_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
    akey
    0.35
    gems
    0.33
    alleng
    0.32
    jeta
    0.30
     איי
    0.30
     سمجھتے
    0.30
    textAllCaps
    0.29
    
    0.29
    parachute
    0.29
    addTo
    0.29
    POSITIVE LOGITS
    가
    0.32
    Hik
    0.32
    пора
    0.30
     extractor
    0.29
     extract
    0.29
    内部
    0.29
     nz
    0.29
    返
    0.29
    Radi
    0.28
     void
    0.28
    Activations Density 0.002%

    No Known Activations