© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10677
    Prev
    Next
    INDEX
    Explanations

    common helper verbs that often point to a more important verb

    oai_token-act-pair · gemini-2.0-flash

    code or programming language syntax

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

    say "the"

    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
    ✷
    -0.57
    ByPrimaryKey
    -0.47
    
    -0.47
    msgTypes
    -0.46
     estimés
    -0.46
    はじめに
    -0.45
    ssos
    -0.44
    حياتها
    -0.43
    thy
    -0.43
    ุง
    -0.43
    POSITIVE LOGITS
     the
    1.66
    новништво
    0.71
    الدراسه
    0.65
    LayoutStyle
    0.64
    +#+#
    0.62
    tothe
    0.59
    routeProvider
    0.58
    endforeach
    0.58
     ofthe
    0.58
    ſelves
    0.56
    Activations Density 1.646%

    No Known Activations