© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 132001
    Prev
    Next
    INDEX
    Explanations

    UCR Program)

    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_6_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
    ר
    0.93
    ли
    0.89
    д
    0.84
    ૩
    0.81
    де
    0.81
    р
    0.80
    ąc
    0.77
    фе
    0.75
     диамет
    0.75
    د
    0.75
    POSITIVE LOGITS
     are
    1.05
    \
    1.05
    '
    0.91
    -
    0.76
    are
    0.66
    \")
    0.62
    (
    0.62
    plication
    0.58
    ag
    0.57
    ı
    0.57
    Activations Density 0.000%

    No Known Activations