© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104470
    Prev
    Next
    INDEX
    Explanations

    Roe v. Wade

    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_1_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
    కి
    1.05
    发挥
    0.98
    冷静
    0.97
    侪
    0.96
    它
    0.96
     将
    0.94
    但这
    0.94
    <
    0.92
    不仅
    0.91
    出品
    0.91
    POSITIVE LOGITS
    an
    1.78
    c
    1.71
    p
    1.67
    s
    1.63
    is
    1.59
    n
    1.55
    g
    1.45
    se
    1.45
    ק
    1.42
    on
    1.41
    Activations Density 0.000%

    No Known Activations