© 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. 11037
    Prev
    Next
    INDEX
    Explanations

    descriptions of tumors and cancer cells

    oai_token-act-pair · gemini-2.0-flash

    medical/scientific texts

    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
    Enllaces
    -0.64
    gdx
    -0.63
    Geplaatst
    -0.60
     RouterModule
    -0.60
    OGND
    -0.57
     виправивши
    -0.57
    enumi
    -0.55
    MemoryWarning
    -0.55
     Basta
    -0.54
    Hauptartikel
    -0.53
    POSITIVE LOGITS
    Personendaten
    0.62
     AssemblyCulture
    0.61
    eur
    0.50
    webElementXpaths
    0.49
     reactants
    0.49
    URIComponent
    0.47
     Curs
    0.47
     otomatig
    0.46
    amor
    0.45
     ground
    0.45
    Activations Density 1.620%

    No Known Activations