© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4573
    Prev
    Next
    INDEX
    Explanations

    code related to the Windows operating system

    oai_token-act-pair · gemini-2.0-flash

    Windows

    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
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.72
    bewerken
    -0.71
    parsedMessage
    -0.71
     nakalista
    -0.69
     presidencial
    -0.69
     CreateTagHelper
    -0.69
     utafitiHapana
    -0.68
    retweeted
    -0.67
    UserScript
    -0.67
    principalColumn
    -0.66
    POSITIVE LOGITS
     forms
    0.76
     form
    0.74
     Form
    0.69
    form
    0.60
     Forms
    0.60
    Form
    0.55
    forms
    0.55
    Forms
    0.54
     fon
    0.53
    FORMS
    0.52
    Activations Density 0.293%

    No Known Activations