© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16472
    Prev
    Next
    INDEX
    Explanations

    decision or judgment

    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_34_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
    रिक्त
    0.37
    死
    0.36
    东南
    0.34
     subcellular
    0.34
    電源
    0.33
    verm
    0.33
    vues
    0.33
    预览
    0.33
    +"\
    0.32
    точно
    0.32
    POSITIVE LOGITS
     keputusan
    0.70
     decisions
    0.63
     decisione
    0.63
     decisão
    0.62
     beslut
    0.61
     decision
    0.61
    決定
    0.61
     decisión
    0.59
     Decisions
    0.59
     Entscheidung
    0.59
    Activations Density 0.046%

    No Known Activations