© 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. 10916
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is offering assistance or negotiating with another person.

    oai_token-act-pair · gemini-2.0-flash

    non-standard or technical terms

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

    Real estate

    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
     AssemblyCulture
    -0.65
    RTLD
    -0.65
     crdi
    -0.63
     Pute
    -0.61
     whoſe
    -0.60
    EditorBrowsable
    -0.59
     referenties
    -0.59
    BeginInit
    -0.59
    glut
    -0.57
    NOPQRST
    -0.56
    POSITIVE LOGITS
     jaj
    0.46
    styleable
    0.44
     calific
    0.44
     ExecuteAsync
    0.44
    ANCA
    0.44
    localctx
    0.43
    Polo
    0.41
    férences
    0.41
    kam
    0.40
     pay
    0.40
    Activations Density 2.085%

    No Known Activations