© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261056
    Prev
    Next
    INDEX
    Explanations

    harmlessness

    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_5_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
    ig
    1.91
    k
    1.89
    ac
    1.73
    at
    1.67
    in
    1.66
    f
    1.55
    et
    1.45
    ap
    1.44
    ens
    1.43
    ang
    1.42
    POSITIVE LOGITS
    ),
    1.09
    ){
    1.09
    はなく
    1.06
     вверх
    1.05
     ஆகும்
    1.03
    もちろん
    1.03
     Может
    1.00
     पद्धतीने
    1.00
    ));
    1.00
     ممكن
    0.99
    Activations Density 0.008%

    No Known Activations