© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 203110
    Prev
    Next
    INDEX
    Explanations

    reaver / bringer

    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
    n
    0.81
    상
    0.79
    ᚋ
    0.76
    EMAN
    0.75
     زمانے
    0.75
    nél
    0.74
    nagar
    0.74
    の設定
    0.74
    CONFIGURATION
    0.74
    nCount
    0.73
    POSITIVE LOGITS
    ים
    1.02
    ς
    0.99
    s
    0.92
    </h3>
    0.90
     I
    0.88
     has
    0.87
    م
    0.84
     l
    0.80
    ра
    0.80
    </h2>
    0.79
    Activations Density 0.003%

    No Known Activations