© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3363
    Prev
    Next
    INDEX
    Explanations

    names of government departments and offices, particularly when followed by "of"

    oai_token-act-pair · gemini-2.0-flash

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    contentLoaded
    -0.71
     SwitchCompat
    -0.69
    RenderAtEndOf
    -0.68
    ArrowToggle
    -0.65
    WireFormatLite
    -0.62
    ^*)
    -0.60
    Autoritní
    -0.60
    httphttps
    -0.59
    TintMode
    -0.59
    Controllo
    -0.59
    POSITIVE LOGITS
    tagHelperRunner
    0.47
    typename
    0.45
    illium
    0.42
    dens
    0.40
    no
    0.40
    coy
    0.40
    ธ
    0.40
    byshev
    0.39
     survives
    0.39
    Dtor
    0.39
    Activations Density 1.176%

    No Known Activations