© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14652
    Prev
    Next
    INDEX
    Explanations

    academic papers and citations

    oai_token-act-pair · gemini-2.0-flash

    scientific context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    contentLoaded
    -0.96
     Drapeau
    -0.92
    出版年
    -0.89
    verwijspagina
    -0.84
    ⓧ
    -0.73
     Савезне
    -0.67
    MessageOf
    -0.65
    OGND
    -0.65
     AssemblyCulture
    -0.63
     Wiktionnaire
    -0.62
    POSITIVE LOGITS
     chimique
    0.50
     químicas
    0.49
     חיצוניים
    0.49
    ArgsConstructor
    0.45
    ضايا
    0.43
    geot
    0.41
     привле
    0.41
    Leaf
    0.41
    Indent
    0.41
     TextEditing
    0.41
    Activations Density 1.363%

    No Known Activations