© 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. 86232
    Prev
    Next
    INDEX
    Explanations

    microclimate or processors

    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
     in
    0.90
    da
    0.81
     في
    0.69
    在
    0.69
    ről
    0.67
     inns
    0.65
     reorgan
    0.63
     lumin
    0.62
    يش
    0.62
     jeopard
    0.61
    POSITIVE LOGITS
    شتی
    0.63
    ほか
    0.63
    </h5>
    0.60
    یم
    0.60
     potrebno
    0.59
     बाकी
    0.58
    ری
    0.57
    ാല
    0.56
    Clic
    0.56
    رمی
    0.55
    Activations Density 0.002%

    No Known Activations