© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11133
    Prev
    Next
    INDEX
    Explanations

    mentions of beta and alpha, followed either by a hyphen or other word fragments, in scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    biochemistry related terminology

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     فريبيس
    -0.84
     الدولى
    -0.83
    ImageContext
    -0.81
    ChildScrollView
    -0.80
    Geplaatst
    -0.74
    RenderAtEndOf
    -0.73
     HttpNotFound
    -0.65
     Италијани
    -0.64
    يميديا
    -0.59
    FXMLLoader
    -0.59
    POSITIVE LOGITS
    ungan
    0.55
    igar
    0.51
    Ծանոթ
    0.51
    ModelAdmin
    0.51
     Verenig
    0.50
    yargs
    0.48
    stoma
    0.46
    InputBorder
    0.46
     claro
    0.45
    ্প
    0.44
    Activations Density 1.235%

    No Known Activations