© 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
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9888
    Prev
    Next
    INDEX
    Explanations

    terms related to the state of an application, and XML attributes

    oai_token-act-pair · gemini-2.0-flash

    Android development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    InstanceState
    -0.93
     CreateTagHelper
    -0.93
    ValueStyle
    -0.85
    脚注の使い方
    -0.73
    rungsseite
    -0.68
    parsedMessage
    -0.65
     виправивши
    -0.64
     Walkover
    -0.62
    AddHtmlAttribute
    -0.61
    tagHelperRunner
    -0.60
    POSITIVE LOGITS
     varandra
    0.50
     nakalista
    0.49
    tadır
    0.49
    Caratteristiche
    0.49
    feitura
    0.47
     réaliste
    0.47
     déclarations
    0.47
     hjäl
    0.45
    lse
    0.45
    forRoot
    0.44
    Activations Density 0.063%

    No Known Activations