© 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
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 63701
    Prev
    Next
    INDEX
    Explanations

    apps, APKs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Key
    0.42
    ByKey
    0.39
    ક્તિ
    0.38
    ⵅ
    0.38
     Dix
    0.37
    指向
    0.37
    Key
    0.37
    Seth
    0.36
     질
    0.36
    Theoretical
    0.36
    POSITIVE LOGITS
    アプリ
    0.46
    aplik
    0.43
     Sousa
    0.43
     приложений
    0.42
    APK
    0.42
    appList
    0.41
     APK
    0.40
     बजकर
    0.39
     app
    0.39
     Wnd
    0.39
    Activations Density 0.001%

    No Known Activations