© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41640
    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_22_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
    云
    0.46
    пры
    0.46
    分析
    0.44
     "
    0.41
    温
    0.41
    仅
    0.41
    更
    0.40
    明
    0.40
    北
    0.40
    飘
    0.39
    POSITIVE LOGITS
     siamo
    0.51
    اسية
    0.49
     supplied
    0.47
    seguir
    0.46
    ುತ್ತದೆ
    0.44
    ៖
    0.43
     SUPPL
    0.43
    ताच
    0.43
     suivre
    0.43
    ளான
    0.42
    Activations Density 0.000%

    No Known Activations