© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8143
    Prev
    Next
    INDEX
    Explanations

    javascript code relating to document click events

    oai_token-act-pair · gemini-2.0-flash

    JavaScript event handlers

    np_token-act-pair-logits · gpt-4o-mini

    Code and scripts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    oth
    -0.56
    brainly
    -0.53
     propOrder
    -0.53
    
    -0.51
    SPJ
    -0.51
    ź
    -0.49
    retty
    -0.48
    assurer
    -0.48
    τει
    -0.48
    ároz
    -0.47
    POSITIVE LOGITS
    jsii
    0.57
     ErrIntOverflow
    0.55
    Marshaller
    0.54
    oa̍t
    0.53
    fromnode
    0.52
     '\\;'
    0.52
    contentLoaded
    0.51
     חיצוניים
    0.51
    twimg
    0.50
     RemoteException
    0.50
    Activations Density 0.770%

    No Known Activations