© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 32198
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_7_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
    cji
    0.54
    یت
    0.54
    েম্ব
    0.52
    𝗘
    0.52
    به
    0.50
    ת
    0.50
    āja
    0.50
    cijas
    0.49
    φα
    0.49
    انی
    0.49
    POSITIVE LOGITS
     සිට
    0.49
     becomes
    0.44
     pendientes
    0.41
     that
    0.41
     drooping
    0.40
     Euclidean
    0.40
     tidy
    0.39
     rife
    0.39
     postaje
    0.39
    </h3>
    0.39
    Activations Density 0.000%

    No Known Activations