© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51003
    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_30_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
     лого
    0.47
    fores
    0.42
    宁波
    0.39
     ဒါ
    0.39
    blems
    0.38
    态度
    0.38
    豌
    0.37
    halo
    0.37
     Sykes
    0.37
    ภ
    0.37
    POSITIVE LOGITS
     material
    0.39
    âmb
    0.36
     leaned
    0.36
    ajar
    0.35
     коммуна
    0.34
     anh
    0.34
     leaning
    0.34
     District
    0.34
     Material
    0.33
    ENIX
    0.33
    Activations Density 0.000%

    No Known Activations