© 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. 13492
    Prev
    Next
    INDEX
    Explanations

    the end of reviews where people are identified

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    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
     InputDecoration
    -0.48
     under
    -0.44
    IsContent
    -0.43
     BrowserModule
    -0.41
     Dazu
    -0.40
    くださいませ
    -0.40
     Davison
    -0.40
    digkeit
    -0.40
     sotto
    -0.40
    Dabei
    -0.39
    POSITIVE LOGITS
     disambiguazione
    0.82
    LLocation
    0.64
    ergies
    0.59
     ويكيپيديا
    0.59
     Walkover
    0.59
    oflavin
    0.58
     createState
    0.57
    AndroidJUnit
    0.56
    postmedia
    0.56
     Rha
    0.56
    Activations Density 0.826%

    No Known Activations