© 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. 2051
    Prev
    Next
    INDEX
    Explanations

    numbers associated with a date or year, possibly within a range

    oai_token-act-pair · gemini-2.0-flash

    words with unusual characters or phonetics

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

    date ranges

    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
     AssemblyCulture
    -0.80
    CodeAttribute
    -0.69
    BufferException
    -0.64
    byen
    -0.62
    ]--;
    -0.62
    الحياه
    -0.58
    IsMutable
    -0.57
    FormTagHelper
    -0.55
     definiti
    -0.54
    RTEX
    -0.53
    POSITIVE LOGITS
    ſelf
    0.64
     Majefty
    0.56
    ſelves
    0.53
    enumi
    0.52
     שוליים
    0.52
     houſe
    0.50
     Thurston
    0.50
     myſelf
    0.50
     perfons
    0.49
    WebElementEntity
    0.48
    Activations Density 0.553%

    No Known Activations