© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133735
    Prev
    Next
    INDEX
    Explanations

    eX words and suffixes

    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_1_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
    o
    1.23
    ;
    1.13
    il
    1.10
    ,}
    1.05
    ,
    1.04
    y
    1.02
    ",
    1.00
    ),
    0.96
    ่ง
    0.92
    ;"
    0.92
    POSITIVE LOGITS
     fabriqu
    1.02
     conscient
    0.95
    नं
    0.95
    το
    0.95
    to
    0.94
     carbure
    0.93
     supérieures
    0.91
     nutrit
    0.90
     materialize
    0.88
     carburetor
    0.87
    Activations Density 0.001%

    No Known Activations