© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 211334
    Prev
    Next
    INDEX
    Explanations

    sp and sp² hybridized orbitals

    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_19_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
    za
    0.47
    িল্লা
    0.45
    day
    0.42
    ke
    0.42
     ges
    0.41
     Risiko
    0.41
    vironment
    0.41
    워
    0.40
     Jos
    0.40
     स्टाइल
    0.40
    POSITIVE LOGITS
     vedit
    0.45
     downregulated
    0.43
     новий
    0.43
    Gosudarstvennyj
    0.42
     unregulated
    0.42
     ಬರುತ್ತ
    0.42
     intrusions
    0.41
    ेंटिस
    0.41
    MEDICAL
    0.41
    രുദ്ധ
    0.41
    Activations Density 0.000%

    No Known Activations