© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9938
    Prev
    Next
    INDEX
    Explanations

    names of specific people and organizations and verbs about the current state

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    org
    -0.34
    Mutable
    -0.33
    der
    -0.33
    offers
    -0.32
     des
    -0.32
     la
    -0.32
     exer
    -0.32
     offers
    -0.31
    нин
    -0.31
    ene
    -0.31
    POSITIVE LOGITS
    contentLoaded
    1.06
     disambiguazione
    1.04
    tagHelperRunner
    1.00
    GEBURTSDATUM
    0.94
    Демографія
    0.83
    XmlAccessType
    0.82
     Roskov
    0.82
     تضيفلها
    0.81
     Chwiliwch
    0.80
    ContentAsync
    0.79
    Activations Density 5.615%

    No Known Activations