© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12015
    Prev
    Next
    INDEX
    Explanations

    references to people in need of medical or educational support

    oai_token-act-pair · gemini-2.0-flash

    specific references in code-related contexts

    np_token-act-pair-logits · gpt-4o-mini

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    rxjs
    -0.47
    endosi
    -0.44
     onCreateView
    -0.43
    DoubleQuotes
    -0.40
    Gruppen
    -0.37
    gatsby
    -0.37
     werd
    -0.37
    XmlAccessType
    -0.37
    ungsver
    -0.36
    niv
    -0.36
    POSITIVE LOGITS
    ConstraintMaker
    0.93
    tagHelperRunner
    0.83
     Roskov
    0.79
     shouldn
    0.77
     should
    0.75
     which
    0.74
     who
    0.73
     hefyd
    0.70
     IBOutlet
    0.70
    abestanden
    0.68
    Activations Density 2.376%

    No Known Activations