© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6382
    Prev
    Next
    INDEX
    Explanations

    code for finding elements in an Android layout

    oai_token-act-pair · gemini-2.0-flash

    )

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    enschappelijke
    -0.65
    PyExc
    -0.59
     roll
    -0.53
    istoitu
    -0.52
     محفوظة
    -0.52
    coroutines
    -0.52
    ')['
    -0.51
    ImageContext
    -0.51
    )['
    -0.51
    Jeografia
    -0.50
    POSITIVE LOGITS
    WaitGroup
    0.71
    BeginContext
    0.67
    RegistryLite
    0.56
    WillAppear
    0.52
    AlterField
    0.52
    IUrlHelper
    0.50
     contre
    0.49
     مواليد
    0.48
     NSCoder
    0.48
     Guel
    0.48
    Activations Density 1.355%

    No Known Activations