© 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. 203804
    Prev
    Next
    INDEX
    Explanations

    blonde hair

    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
    _
    1.07
    도
    0.96
     in
    0.86
    IN
    0.78
    인
    0.75
     चोपड़ा
    0.73
     degr
    0.70
     block
    0.70
    STER
    0.69
     inflection
    0.69
    POSITIVE LOGITS
    м
    1.01
    <unused443>
    0.96
     ሃ
    0.89
    <unused75>
    0.88
     multiSelectList
    0.87
    م
    0.86
    <unused2182>
    0.83
    és
    0.82
     auxqu
    0.82
     vivió
    0.80
    Activations Density 0.001%

    No Known Activations