© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13572
    Prev
    Next
    INDEX
    Explanations

    words and phrases expressing gratitude and affection

    oai_token-act-pair · gemini-2.0-flash

    positive expressions

    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
     ་་
    -0.70
     ―――――
    -0.66
    enumii
    -0.65
    PhysRevLett
    -0.62
     ↔
    -0.61
     مشين
    -0.61
     Opa
    -0.61
     milo
    -0.60
     ::=
    -0.60
    cipar
    -0.60
    POSITIVE LOGITS
    лтемелер
    0.50
    LabelTagHelper
    0.44
    ⓧ
    0.44
     resourceCulture
    0.43
     May
    0.40
    createCanvas
    0.37
    NavController
    0.36
    assertArray
    0.36
    roux
    0.35
     препратки
    0.35
    Activations Density 2.487%

    No Known Activations