© 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. 4536
    Prev
    Next
    INDEX
    Explanations

    the syntax and keywords used in a programming language

    oai_token-act-pair · gemini-2.0-flash

    class declarations and structure in code

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

    code colons/arrows

    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
     nakalista
    -0.85
    Geplaatst
    -0.83
    fromnode
    -0.77
     مشين
    -0.72
     pleaſure
    -0.68
     defStyle
    -0.67
     resourceCulture
    -0.67
     CreateTagHelper
    -0.67
    +#+#
    -0.67
    цездатний
    -0.65
    POSITIVE LOGITS
     Project
    0.55
    ględ
    0.52
     A
    0.52
     E
    0.51
     Le
    0.49
    vica
    0.49
     Which
    0.48
    amodel
    0.48
     esquem
    0.48
     La
    0.47
    Activations Density 1.729%

    No Known Activations