© 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. 2920
    Prev
    Next
    INDEX
    Explanations

    the word "on" followed by a hyphen or the letters "site", "call" or any word ending in "-ion"

    oai_token-act-pair · gemini-2.0-flash

    on

    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
     فريبيس
    -1.05
     Wikimedijinoj
    -0.98
    AndEndTag
    -0.97
     doubtnut
    -0.96
    yntaxException
    -0.85
    
    -0.85
    OGND
    -0.82
     Jefus
    -0.82
     ProtoMessage
    -0.81
    IUrlHelper
    -0.81
    POSITIVE LOGITS
    site
    0.60
     tap
    0.55
    -
    0.55
     site
    0.53
     di
    0.50
     hand
    0.49
     view
    0.48
    •
    0.45
     property
    0.45
     sus
    0.45
    Activations Density 0.834%

    No Known Activations