© 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. 6730
    Prev
    Next
    INDEX
    Explanations

    Android application lifecycle callbacks

    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
     post
    0.40
     sou
    0.40
    thiophen
    0.38
     rutina
    0.37
    土
    0.36
    舟
    0.34
     वाता
    0.34
     site
    0.34
     ut
    0.34
    POST
    0.33
    POSITIVE LOGITS
     MyApplication
    0.40
    ᱩ
    0.40
     Crews
    0.39
     Confucian
    0.39
     Fidelity
    0.38
    装着
    0.38
     hazel
    0.38
     Gita
    0.37
     khat
    0.37
     releases
    0.37
    Activations Density 0.001%

    No Known Activations