© 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. 4322
    Prev
    Next
    INDEX
    Explanations

    descriptions of features of a building

    oai_token-act-pair · gemini-2.0-flash

    technical terms or components from a specific domain

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

    Technical documents/code fragments

    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
     виправивши
    -0.63
    Aholisi
    -0.57
     NSCoder
    -0.50
    nhi
    -0.50
     préfé
    -0.50
    thâu
    -0.49
    inquirer
    -0.48
     censo
    -0.47
     navigazione
    -0.47
    migrationBuilder
    -0.44
    POSITIVE LOGITS
    BufferException
    0.61
    createComponent
    0.61
    modelBuilder
    0.57
    Portale
    0.57
    Portail
    0.56
    JspWriter
    0.54
    niczy
    0.54
     createSlice
    0.54
     domes
    0.53
    shields
    0.53
    Activations Density 1.576%

    No Known Activations