© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13288
    Prev
    Next
    INDEX
    Explanations

    words related to creating and showcasing visual content

    oai_token-act-pair · gemini-2.0-flash

    language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     كومونز
    -0.60
    InitVars
    -0.56
     Italijani
    -0.56
     NgModule
    -0.54
    rouvez
    -0.54
     initComponents
    -0.54
     InputDecoration
    -0.54
    ėd
    -0.50
    matorium
    -0.50
     đương
    -0.50
    POSITIVE LOGITS
     language
    2.84
     Language
    2.42
    language
    2.42
    Language
    2.30
     LANGUAGE
    2.20
    LANGUAGE
    1.93
    语言
    1.91
     langage
    1.87
     lenguaje
    1.84
     languages
    1.79
    Activations Density 2.685%

    No Known Activations