© 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. 12819
    Prev
    Next
    INDEX
    Explanations

    code snippets with a mix of numbers, letters, and operators

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks and notation

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

    Numbers

    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
     незавершена
    -0.89
    SourceChecksum
    -0.89
    StoryboardSegue
    -0.86
    rawDesc
    -0.79
    verwijspagina
    -0.79
    StructEnd
    -0.76
    InjectAttribute
    -0.73
     GenerationType
    -0.72
    providedIn
    -0.71
     שוליים
    -0.70
    POSITIVE LOGITS
    .,
    0.63
    .:
    0.53
    .;
    0.52
    ./
    0.48
     altında
    0.45
    .),
    0.43
    .).
    0.42
     conscientes
    0.41
    plaat
    0.40
     də
    0.40
    Activations Density 4.058%

    No Known Activations