© 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. 74944
    Prev
    Next
    INDEX
    Explanations

    text and image inputs

    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
     INT
    0.27
    imd
    0.26
    
    0.26
    ￠
    0.25
     INS
    0.25
    ઈ
    0.25
     transporting
    0.24
    Int
    0.24
     ইন্
    0.24
    odus
    0.24
    POSITIVE LOGITS
    -->'
    0.29
    ദ്ധ
    0.29
     Temos
    0.28
     znak
    0.27
    rish
    0.27
    ]^{
    0.25
    rzym
    0.25
     bł
    0.25
     відпо
    0.25
     luft
    0.24
    Activations Density 0.013%

    No Known Activations