© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1237
    Prev
    Next
    INDEX
    Explanations

    Android ViewModel lifecycle

    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_39_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
    TreeClassifier
    0.40
    茦
    0.40
    菄
    0.39
     piti
    0.39
    日至
    0.39
    机票
    0.38
    revalidator
    0.38
     جاسک
    0.38
     nematodes
    0.36
     Tori
    0.36
    POSITIVE LOGITS
     Saved
    0.46
     ire
    0.38
     inteligencia
    0.38
     சர்வதேச
    0.38
    ℤ
    0.37
    Service
    0.37
     সদ্য
    0.37
    Looking
    0.37
    甑
    0.36
    wood
    0.36
    Activations Density 0.002%

    No Known Activations