© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 78493
    Prev
    Next
    INDEX
    Explanations

    equation / expression solving

    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
    ):(
    0.29
    EDS
    0.29
     hObject
    0.28
     副
    0.28
    ៅ
    0.27
     Marcelo
    0.27
     Mould
    0.27
    ンドン
    0.27
    ):\
    0.27
    Marcel
    0.26
    POSITIVE LOGITS
    并将
    0.29
    put
    0.28
     reasonably
    0.28
    뛰
    0.28
    datatables
    0.27
    鴿
    0.27
     그리고
    0.27
    aisi
    0.27
    侬
    0.26
    ünd
    0.26
    Activations Density 0.009%

    No Known Activations