© 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. 10929
    Prev
    Next
    INDEX
    Explanations

    academic publications, specifically conference proceedings

    oai_token-act-pair · gemini-2.0-flash

    technical terminology and specific nouns

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

    conference proceedings

    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
    Демографія
    -0.77
     autorytatywna
    -0.66
     Atten
    -0.57
    нрави
    -0.57
    PreAuthorize
    -0.55
     attendees
    -0.55
     attendance
    -0.53
     hObject
    -0.53
    thums
    -0.52
     attended
    -0.52
    POSITIVE LOGITS
    Britannique
    0.57
     Lauter
    0.54
    localctx
    0.49
     européenne
    0.49
    asyarakat
    0.49
    transQ
    0.48
     />\
    0.48
     poffible
    0.48
    Clik
    0.47
    WireFormatLite
    0.47
    Activations Density 0.891%

    No Known Activations