© 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. 211581
    Prev
    Next
    INDEX
    Explanations

    bonds and suffixes

    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
    де
    1.34
    d
    1.33
    ли
    1.23
    ה
    1.22
    ל
    1.17
    lə
    1.16
    lma
    1.16
    g
    1.16
    า
    1.16
    ه
    1.14
    POSITIVE LOGITS
     That
    1.09
    ،
    1.06
    with
    1.05
    that
    1.05
     as
    1.04
    and
    1.03
     be
    1.02
    مس
    0.99
    ร
    0.98
    </h3>
    0.98
    Activations Density 0.038%

    No Known Activations