© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13862
    Prev
    Next
    INDEX
    Explanations

    decimal percentages

    oai_token-act-pair · gemini-2.0-flash

    obscure or specialized terms

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

    percentages

    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
     single
    -0.59
     Single
    -0.52
    Single
    -0.49
     Active
    -0.48
     Sy
    -0.47
    ️
    -0.46
    "}")
    -0.45
     K
    -0.44
    single
    -0.43
     Sign
    -0.43
    POSITIVE LOGITS
     Shakspeare
    0.79
    AnchorStyles
    0.73
    ArrowToggle
    0.71
    potranspiration
    0.69
     Италијани
    0.69
     Interpol
    0.69
     Esau
    0.66
     chapels
    0.66
     purpoſe
    0.64
     papyrus
    0.64
    Activations Density 1.526%

    No Known Activations