© 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. 3594
    Prev
    Next
    INDEX
    Explanations

    terms in the document that describe investigations and story narratives

    oai_token-act-pair · gemini-2.0-flash

    leading

    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
     ویکی‌پدیا
    -0.67
    MemoryWarning
    -0.59
    eeq
    -0.58
    Unmarshaller
    -0.57
    DrawerToggle
    -0.57
    viewDidLoad
    -0.54
    XMLSchema
    -0.54
     ویکی‌پدیای
    -0.54
     Affirmative
    -0.53
    UserScript
    -0.53
    POSITIVE LOGITS
     leading
    3.16
     lead
    2.88
    leading
    2.84
     Leading
    2.81
    Leading
    2.75
     leads
    2.58
    lead
    2.48
     Lead
    2.42
    Lead
    2.38
     Leads
    2.36
    Activations Density 4.731%

    No Known Activations