© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 126920
    Prev
    Next
    INDEX
    Explanations

    orange, 远, consumption

    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
    و
    0.87
    z
    0.80
    d
    0.71
    י
    0.71
    𝓼
    0.71
    ки
    0.71
    j
    0.71
    ch
    0.68
    ات
    0.68
    ุ
    0.68
    POSITIVE LOGITS
    </h5>
    0.62
    and
    0.59
    april
    0.57
    ρίες
    0.57
    ok
    0.57
    </h3>
    0.55
    ara
    0.54
    SpringBoot
    0.54
    প্তরের
    0.54
    怎麼樣
    0.53
    Activations Density 0.000%

    No Known Activations