© 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. 7205
    Prev
    Next
    INDEX
    Explanations

    references to UK public sector institutions and legislation and commentary related to those bodies

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    ConstraintMaker
    -0.75
    TintMode
    -0.71
     }{@
    -0.70
    EndInit
    -0.65
    sidemargin
    -0.65
    ThroughAttribute
    -0.61
     تضيفلها
    -0.60
    دانشنامهٔ
    -0.57
     @"/
    -0.56
     Theſe
    -0.56
    POSITIVE LOGITS
     gambe
    0.51
    ropoda
    0.51
     uğ
    0.48
     épaules
    0.45
    DIPSETTING
    0.45
    jería
    0.44
     je
    0.44
     pulang
    0.44
     réc
    0.43
     master
    0.43
    Activations Density 2.339%

    No Known Activations