© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58273
    Prev
    Next
    INDEX
    Explanations

    common sensetolerance

    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_11_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
    が必要
    0.63
     ফেসবুক
    0.61
    of
    0.60
    точка
    0.60
    elem
    0.59
    োর্ট
    0.56
    ]))
    0.54
    因子
    0.54
    umbers
    0.53
    amaks
    0.53
    POSITIVE LOGITS
     D
    0.67
     delegations
    0.64
     P
    0.60
     F
    0.59
     demonstra
    0.57
     demonstrations
    0.56
     fysis
    0.56
     delegation
    0.55
     mø
    0.55
     fys
    0.55
    Activations Density 0.001%

    No Known Activations