© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223073
    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_10_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
    remember
    0.50
    ή
    0.49
    schild
    0.47
    ριν
    0.47
    ᾷ
    0.47
    sign
    0.45
     richiede
    0.45
    ंप
    0.45
    ζει
    0.45
    λαμβ
    0.44
    POSITIVE LOGITS
    از
    0.49
    ುಕ
    0.46
     infections
    0.44
    这话
    0.44
     ક્લિક
    0.44
     น้ำ
    0.42
     éditions
    0.41
    .'),
    0.40
    Қ
    0.40
    وما
    0.39
    Activations Density 0.000%

    No Known Activations