© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12286
    Prev
    Next
    INDEX
    Explanations

    words with strong positive or negative descriptive power, including words indicating importance and technical terms

    oai_token-act-pair · gemini-2.0-flash

    magnitude

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     pageContext
    -0.47
     ogn
    -0.45
     indexed
    -0.44
     mods
    -0.44
    HttpDelete
    -0.44
    격
    -0.43
     GenerationType
    -0.43
     sigui
    -0.43
     murni
    -0.43
    urangan
    -0.42
    POSITIVE LOGITS
    enumi
    0.73
    IBOutlet
    0.65
    tagHelper
    0.59
    VersionUID
    0.54
    !*\
    0.54
    +'</
    0.53
    ThroughAttribute
    0.52
    BeginContext
    0.52
    UnknownFieldSet
    0.52
    
    0.52
    Activations Density 20.152%

    No Known Activations