© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 199329
    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_50_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
    敲
    0.42
    otá
    0.38
     palpable
    0.38
    턴
    0.38
     triumphs
    0.37
     벡터
    0.37
     onTap
    0.37
     vectors
    0.37
    ivative
    0.36
    تی
    0.36
    POSITIVE LOGITS
    🕑
    0.40
     américains
    0.38
    Certification
    0.38
    ⑰
    0.36
    Kam
    0.35
    諳
    0.35
    iddi
    0.35
    ⑬
    0.35
    minister
    0.35
    KAM
    0.35
    Activations Density 0.000%

    No Known Activations