© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11337
    Prev
    Next
    INDEX
    Explanations

    terms related to mobile application development

    oai_token-act-pair · gemini-2.0-flash

    mobile app development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     aplikacji
    -0.85
     apps
    -0.83
     aplicativos
    -0.80
     software
    -0.80
     app
    -0.79
     Apps
    -0.78
     logiciels
    -0.76
     Websites
    -0.75
    websites
    -0.75
    アプリ
    -0.74
    POSITIVE LOGITS
    rawDesc
    0.55
     gynnwys
    0.50
    İstinadlar
    0.48
    GraphicsUnit
    0.45
    chle
    0.45
    ритори
    0.44
     Mos
    0.42
    +#+
    0.42
    dhist
    0.42
    sizeCache
    0.41
    Activations Density 2.876%

    No Known Activations