© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 37252
    Prev
    Next
    INDEX
    Explanations

    US presidents election

    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_3_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
    ’
    1.09
     for
    0.86
     (“
    0.81
     e
    0.78
    '
    0.78
     (
    0.77
     da
    0.75
     n
    0.74
     y
    0.74
     del
    0.74
    POSITIVE LOGITS
    ne
    1.15
    st
    1.13
    t
    1.12
    r
    0.95
    c
    0.94
    d
    0.89
    j
    0.88
    v
    0.87
    ad
    0.85
    s
    0.84
    Activations Density 0.014%

    No Known Activations