© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46459
    Prev
    Next
    INDEX
    Explanations

    action hero movies

    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_3_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
    ,
    0.63
     solvers
    0.61
     to
    0.55
     as
    0.55
     problems
    0.55
    ERSON
    0.55
     enigma
    0.55
    да
    0.54
    =>
    0.54
     aftermarket
    0.53
    POSITIVE LOGITS
    al
    0.88
    alco
    0.84
    it
    0.84
    n
    0.78
    itism
    0.77
    ק
    0.71
    ਲ
    0.70
    ات
    0.68
     Ал
    0.68
    น
    0.66
    Activations Density 0.006%

    No Known Activations