© 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. 8548
    Prev
    Next
    INDEX
    Explanations

    tables with numerical data

    oai_token-act-pair · gemini-2.0-flash

    numerical values and identifiers

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

    Numbers 0 and 1

    np_max-act-logits · gemini-2.0-flash

    spaces

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    IUrlHelper
    -0.98
    ConstraintMaker
    -0.91
     تضيفلها
    -0.91
     CreateTagHelper
    -0.88
     transfieras
    -0.86
    UnsafeEnabled
    -0.82
    цездатний
    -0.82
    styleType
    -0.75
    rungsseite
    -0.75
     للاسماء
    -0.74
    POSITIVE LOGITS
    0
    0.57
    1
    0.55
     universale
    0.52
     ledig
    0.49
     iniquity
    0.45
     himmel
    0.45
     industrious
    0.43
     one
    0.43
    wertig
    0.43
     ši
    0.43
    Activations Density 6.274%

    No Known Activations