© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 43067
    Prev
    Next
    INDEX
    Explanations

    expert in

    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_22_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
     kdy
    0.42
     kilograms
    0.38
     them
    0.38
     fats
    0.38
    minsize
    0.38
     equivale
    0.37
    ժ
    0.37
     انھیں
    0.37
    uaje
    0.37
     ovvero
    0.37
    POSITIVE LOGITS
     wak
    0.42
    ]))
    0.41
     관
    0.40
     البته
    0.40
     Nox
    0.40
     Serien
    0.40
    佔
    0.40
    が多い
    0.39
     பெண்
    0.39
     pax
    0.39
    Activations Density 0.004%

    No Known Activations