© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6072
    Prev
    Next
    INDEX
    Explanations

    the word "group," often in the context of research

    oai_token-act-pair · gemini-2.0-flash

    group

    np_max-act · gemini-2.0-flash

    group

    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_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     group
    -1.28
     Group
    -0.92
    group
    -0.84
    Group
    -0.75
     non
    -0.68
    .
    -0.63
     groups
    -0.63
     former
    -0.63
     low
    -0.63
     a
    -0.63
    POSITIVE LOGITS
    UserScript
    1.41
    WebVitals
    1.30
     propOrder
    1.26
    WebControls
    1.24
    IUrlHelper
    1.22
    تقاوى
    1.19
     avoient
    1.18
    featureID
    1.18
     autorytatywna
    1.16
     étoient
    1.14
    Activations Density 2.030%

    No Known Activations