© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10041
    Prev
    Next
    INDEX
    Explanations

    words related to authority, positions of power and control

    oai_token-act-pair · gemini-2.0-flash

    rule

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     FetchType
    -0.63
    دانشنامهٔ
    -0.58
    BagConstraints
    -0.53
    ANDUM
    -0.53
    UpInside
    -0.50
    ILEY
    -0.48
    tableFuture
    -0.48
    lgari
    -0.47
    lossary
    -0.47
    demment
    -0.47
    POSITIVE LOGITS
     rule
    1.74
    rule
    1.53
     ruled
    1.46
     ruling
    1.43
     Rule
    1.40
    Rule
    1.38
     RULE
    1.36
    RULE
    1.36
     rules
    1.33
    ruled
    1.30
    Activations Density 5.210%

    No Known Activations