© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10908
    Prev
    Next
    INDEX
    Explanations

    numbers, often with decimals, units, or prefixes

    oai_token-act-pair · gemini-2.0-flash

    non-English words or special characters

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

    Numerical measurements

    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
    ///</
    -0.53
    EndInit
    -0.52
     BoxFit
    -0.50
    scriptcase
    -0.48
    .*")]
    -0.48
    icordia
    -0.47
    yntaxException
    -0.47
    frameCount
    -0.46
     kic
    -0.46
     فريبيس
    -0.45
    POSITIVE LOGITS
     preocupes
    0.64
     >=",
    0.63
    بوابة
    0.59
    Personendaten
    0.56
     olsun
    0.56
    évaluateur
    0.52
    发表于
    0.52
     étoit
    0.52
    réhen
    0.50
     pinulongan
    0.50
    Activations Density 0.123%

    No Known Activations