© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124588
    Prev
    Next
    INDEX
    Explanations

    chalet, etiquette

    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
    ין
    0.80
    urile
    0.77
    ющих
    0.72
    ى
    0.71
    க்கு
    0.70
    ارش
    0.68
    يء
    0.68
    こと
    0.67
    ле
    0.66
    ின்
    0.66
    POSITIVE LOGITS
    K
    0.84
    Р
    0.82
    P
    0.81
    B
    0.77
     be
    0.76
    G
    0.76
    that
    0.70
    Service
    0.70
     for
    0.70
    Ρ
    0.69
    Activations Density 0.000%

    No Known Activations