© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7843
    Prev
    Next
    INDEX
    Explanations

    code related to configuration and tuning parameters, particularly those involving timers and sizes, referenced by the string "tuning"

    oai_token-act-pair · gemini-2.0-flash

    contextual programming terms

    np_token-act-pair-logits · gpt-4o-mini

    code tuning parameters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     <=",
    -0.72
    Rhestr
    -0.71
    المكان
    -0.67
    yntaxException
    -0.66
    AddTagHelper
    -0.66
    SharedDtor
    -0.65
    RenderAtEndOf
    -0.64
    verwijspagina
    -0.59
    prepareStatement
    -0.57
    tagHelperRunner
    -0.57
    POSITIVE LOGITS
    ⎨
    0.51
    spół
    0.50
    BeginContext
    0.50
    Step
    0.49
     bén
    0.47
    duma
    0.47
    îtra
    0.47
     step
    0.47
     sää
    0.47
     étape
    0.46
    Activations Density 7.596%

    No Known Activations