© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4130
    Prev
    Next
    INDEX
    Explanations

    a variety of numerical expressions

    oai_token-act-pair · gemini-2.0-flash

    technical terms and programming-related concepts

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

    digits

    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
    richTextPanel
    -0.74
    NTIS
    -0.72
    tagHelperRunner
    -0.71
    ftagPool
    -0.68
    TagMode
    -0.65
    InsertCommand
    -0.63
     nargin
    -0.61
    ilares
    -0.61
    '])->
    -0.58
     double
    -0.56
    POSITIVE LOGITS
     HttpNotFound
    0.55
    ArgsConstructor
    0.52
    Skocz
    0.51
     disambiguazione
    0.48
     שוליים
    0.41
    VersionUID
    0.40
    roek
    0.40
    SerializedName
    0.40
    proba
    0.38
     autos
    0.38
    Activations Density 1.269%

    No Known Activations