© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213630
    Prev
    Next
    INDEX
    Explanations

    demilitarize, democracy, demographic

    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_5_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
    ا۔
    1.38
    τή
    1.30
    on
    1.30
    。
    1.29
    o
    1.22
    ால்
    1.16
    a
    1.14
    arat
    1.13
    مان
    1.11
    வ்வேறு
    1.08
    POSITIVE LOGITS
    t
    1.55
     I
    1.52
     l
    1.41
     i
    1.36
     x
    1.23
    </h2>
    1.18
     f
    1.18
    </td>
    1.16
     as
    1.16
    </a>
    1.14
    Activations Density 0.002%

    No Known Activations