© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76085
    Prev
    Next
    INDEX
    Explanations

    theif best

    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_31_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
    Flatten
    0.29
    ెక్
    0.28
    ुसार
    0.26
    flatten
    0.26
    Missouri
    0.24
    ሙ
    0.24
    lebr
    0.24
     मानक
    0.24
    
    0.23
     perkara
    0.23
    POSITIVE LOGITS
    setContent
    0.24
     allotted
    0.24
    atação
    0.23
     RTE
    0.22
     presento
    0.22
     conteúdos
    0.22
     ক্যাল
    0.22
     strict
    0.21
     Cal
    0.21
     Еўропы
    0.21
    Activations Density 0.001%

    No Known Activations