© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7377
    Prev
    Next
    INDEX
    Explanations

    other and similar connectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     đó
    0.48
     eso
    0.40
    Jennifer
    0.38
    Synchronization
    0.37
     Vestone
    0.36
    %%%
    0.35
    ½
    0.35
     זה
    0.35
    송
    0.34
     ワン
    0.34
    POSITIVE LOGITS
     etc
    0.69
    etc
    0.58
    等等
    0.56
     Etc
    0.54
     usw
    0.52
     आदि
    0.50
     وغیرہ
    0.49
     тощо
    0.48
     ইত্যাদি
    0.47
    等の
    0.46
    Activations Density 0.005%

    No Known Activations