© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 221995
    Prev
    Next
    INDEX
    Explanations

    Nefertiti, Nefertari, Imhotep

    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_10_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
    DanhMucSP
    0.27
     مليار
    0.26
     pouze
    0.25
    รียม
    0.25
    AMENTO
    0.25
     soutenir
    0.24
     frameN
    0.24
    𝖚
    0.24
    tsprec
    0.24
     auxqu
    0.24
    POSITIVE LOGITS
    0
    0.29
    I
    0.28
    if
    0.27
     and
    0.27
    ies
    0.27
     was
    0.25
    ie
    0.25
    m
    0.25
    ll
    0.25
    ikes
    0.24
    Activations Density 0.005%

    No Known Activations