© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89613
    Prev
    Next
    INDEX
    Explanations

    chroma key, law, emperor, kromvojoj

    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
    es
    0.84
    риев
    0.70
    ด
    0.66
    otur
    0.66
    ेलर
    0.63
     فوټبال
    0.63
    ed
    0.62
    au
    0.61
    itores
    0.60
    el
    0.60
    POSITIVE LOGITS
    р
    0.79
    t
    0.73
    K
    0.72
    the
    0.71
    ר
    0.68
    H
    0.66
    to
    0.64
    IS
    0.62
    U
    0.61
    ্ল
    0.61
    Activations Density 0.011%

    No Known Activations