© 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. 6099
    Prev
    Next
    INDEX
    Explanations

    code import statements with double quote delimited strings

    oai_token-act-pair · gemini-2.0-flash

    programming keywords or terms

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

    code/files

    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
    finden
    -0.48
     virke
    -0.47
     برانيه
    -0.45
    UpInside
    -0.45
    mäß
    -0.43
     délic
    -0.42
    Predecesor
    -0.42
    CSRF
    -0.42
    annelse
    -0.42
    licants
    -0.42
    POSITIVE LOGITS
    enterOuterAlt
    0.71
    المناصب
    0.69
     thiệu
    0.67
    boxylic
    0.65
    مصادر
    0.64
    BeginContext
    0.63
    makeConstraints
    0.59
     poveznice
    0.59
    verwijspagina
    0.58
    himu
    0.57
    Activations Density 0.504%

    No Known Activations