© 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. 5108
    Prev
    Next
    INDEX
    Explanations

    words related to computing, software, business, and people with titles.

    oai_token-act-pair · gemini-2.0-flash

    technical terms and concepts

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

    technical content

    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
    $?
    -0.91
    ?).
    -0.90
    ?}
    -0.88
    %?
    -0.80
    .},
    -0.76
    ?</
    -0.75
    ?),
    -0.74
    ?");
    -0.74
    ?):
    -0.73
    //}
    -0.71
    POSITIVE LOGITS
     NSCoder
    0.52
    OGND
    0.48
     AssemblyVersion
    0.47
    Rüyada
    0.47
    ScopeManager
    0.46
     CreateTagHelper
    0.44
    Демографія
    0.44
    Décès
    0.43
     estekak
    0.43
    InputTagHelper
    0.42
    Activations Density 5.139%

    No Known Activations