© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5210
    Prev
    Next
    INDEX
    Explanations

    code related to Android layout XML files

    oai_token-act-pair · gemini-2.0-flash

    Android code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ModelForm
    -0.47
    {$
    -0.47
    ControllerTest
    -0.45
    ($
    -0.44
    manage
    -0.43
    صح
    -0.43
     Negotiating
    -0.42
     Missions
    -0.42
    sell
    -0.41
     lectures
    -0.41
    POSITIVE LOGITS
    bootstrapcdn
    0.79
    PreferredItem
    0.78
    ThroughAttribute
    0.75
     AssemblyCulture
    0.75
    帖最后由
    0.71
     propOrder
    0.70
    IsMutable
    0.69
    FormTagHelper
    0.69
    AndroidJUnit
    0.68
    ValueStyle
    0.68
    Activations Density 15.226%

    No Known Activations