© 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. 5625
    Prev
    Next
    INDEX
    Explanations

    mentions of social issues, especially regarding race and class, as well as geographic locations and organizations linked to conflict.

    oai_token-act-pair · gemini-2.0-flash

    locations

    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
    BeginContext
    -0.66
     ""],
    -0.59
    AndroidJUnit
    -0.57
     resourceCulture
    -0.56
    matchCondition
    -0.55
    InstanceState
    -0.54
    breakpoint
    -0.47
    ERI
    -0.47
     상세
    -0.47
    RenderAtEndOf
    -0.47
    POSITIVE LOGITS
    PreferredItem
    0.71
    edly
    0.62
    __*/
    0.57
    ficulty
    0.57
    Obrázky
    0.56
    onix
    0.55
    oproject
    0.52
    WebpackPlugin
    0.51
    ASHINGTON
    0.51
    ⓧ
    0.51
    Activations Density 1.255%

    No Known Activations