© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3153
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to lists and organization

    oai_token-act-pair · gemini-2.0-flash

    terms related to conferences or events

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

    conferences and gatherings

    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
     autorytatywna
    -0.90
     betweenstory
    -0.75
    SharedDtor
    -0.69
     AssemblyCulture
    -0.65
    TagHelpers
    -0.65
     esternos
    -0.63
     المعيارى
    -0.59
    tagHelperRunner
    -0.57
    脚注の使い方
    -0.56
     disambiguazione
    -0.56
    POSITIVE LOGITS
     seeding
    0.54
     conference
    0.52
     conf
    0.51
    kammer
    0.51
     chamber
    0.51
    Specifier
    0.49
     seed
    0.47
    Conference
    0.47
     Conference
    0.46
    archiviato
    0.46
    Activations Density 2.178%

    No Known Activations