© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 210864
    Prev
    Next
    INDEX
    Explanations

    iron, torches, steam, station

    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_20_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
    l
    0.51
    路
    0.42
    RA
    0.40
    ibis
    0.38
    valid
    0.38
    lina
    0.38
    concurrent
    0.38
    empty
    0.37
    about
    0.37
    ۱
    0.37
    POSITIVE LOGITS
     ඔබට
    0.39
     menikah
    0.38
     pptd
    0.38
     informé
    0.37
     hermosa
    0.37
     hormon
    0.36
     období
    0.36
    tDBOutput
    0.36
     باشید
    0.36
     Stoll
    0.36
    Activations Density 0.000%

    No Known Activations