© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 317
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions surrounded by other words

    oai_token-act-pair · gemini-2.0-flash

    groups of people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Groups
    -1.76
     groups
    -1.63
     GROUPS
    -1.55
    groups
    -1.54
    Group
    -1.52
    Groups
    -1.51
     groupes
    -1.51
     Group
    -1.51
     getGroup
    -1.45
     Gruppe
    -1.43
    POSITIVE LOGITS
     a
    0.59
     
    0.51
     C
    0.47
    ↵
    0.43
    ↵↵
    0.42
     in
    0.41
     (
    0.41
    .
    0.41
     c
    0.39
     A
    0.39
    Activations Density 2.473%

    No Known Activations