© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 4891
    Prev
    Next
    INDEX
    Explanations

    programming and computer terminology connected to the visibility of elements in an interface

    oai_token-act-pair · gemini-2.0-flash

    technical terms related to display attributes

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

    display

    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
     indemnity
    -0.57
    printStackTrace
    -0.54
    IsPostBack
    -0.52
     Dispersion
    -0.52
    webElement
    -0.50
    RepeatedField
    -0.49
     marshmallows
    -0.49
     Indemnity
    -0.49
    AddHtmlAttribute
    -0.48
     محفوظة
    -0.48
    POSITIVE LOGITS
    IsMutable
    0.74
     ModelExpression
    0.72
    tagHelperRunner
    0.61
    IVEREF
    0.58
    Notae
    0.54
     bước
    0.52
    ViewFeatures
    0.50
    рыя
    0.50
     Lightboxes
    0.49
     Fische
    0.49
    Activations Density 3.019%

    No Known Activations