© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13534
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "group" and words associated with it, sometimes related to numbers or statistics

    oai_token-act-pair · gemini-2.0-flash

    Group

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    -2.31
     Group
    -2.27
    group
    -2.20
    Group
    -2.17
     GROUP
    -2.16
    GROUP
    -1.95
     Groups
    -1.92
     groupe
    -1.91
     groups
    -1.88
     grupo
    -1.80
    POSITIVE LOGITS
    ViewFeatures
    0.60
    SourceChecksum
    0.49
    expandindo
    0.48
     autorytatywna
    0.48
    djangoproject
    0.47
    quias
    0.46
     BoxFit
    0.45
     تعدى
    0.43
     CanadaChoose
    0.43
    cshtml
    0.42
    Activations Density 0.844%

    No Known Activations