© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1968
    Prev
    Next
    INDEX
    Explanations

    code from Android software and phone applications

    oai_token-act-pair · gemini-2.0-flash

    Android apps and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     android
    -0.75
     Android
    -0.74
     Xamarin
    -0.65
     iOS
    -0.65
     cellulare
    -0.63
    Android
    -0.62
    android
    -0.61
     smartphone
    -0.60
     iPhone
    -0.59
     ios
    -0.59
    POSITIVE LOGITS
    RenderAtEndOf
    0.63
     Ors
    0.61
     Chwiliwch
    0.55
    contentLoaded
    0.52
    <bos>
    0.51
     FOG
    0.50
     Aja
    0.50
    AnchorStyles
    0.50
     otomatig
    0.48
    PasswordEncoder
    0.48
    Activations Density 0.468%

    No Known Activations