© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7185
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs, often in the context of political actions

    oai_token-act-pair · gemini-2.0-flash

    could

    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
    Negative Logits
    olella
    -0.52
     lyst
    -0.44
     intellectuelle
    -0.43
     ře
    -0.42
    AttributedString
    -0.42
    Sooo
    -0.41
     Trouver
    -0.41
     étrangères
    -0.41
    ptonshire
    -0.41
    さまで
    -0.40
    POSITIVE LOGITS
     CreateTagHelper
    0.84
    انيف
    0.73
    AxisAlignment
    0.71
     виправивши
    0.68
    oredCriteria
    0.66
     Exacts
    0.65
     Савезне
    0.65
    Portail
    0.65
    [++
    0.62
    InvalidProtocol
    0.61
    Activations Density 3.130%

    No Known Activations