© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 134421
    Prev
    Next
    INDEX
    Explanations

    make a big deal

    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_6_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
    c
    1.75
    p
    1.63
    x
    1.57
    to
    1.55
    b
    1.52
    n
    1.46
    g
    1.38
    k
    1.38
    s
    1.36
    st
    1.34
    POSITIVE LOGITS
    ží
    0.94
     který
    0.89
    ياة
    0.86
     Dwight
    0.86
     الدين
    0.84
     قيم
    0.83
    )="
    0.83
    Ví
    0.82
    Qué
    0.81
    Votre
    0.81
    Activations Density 0.000%

    No Known Activations