Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 6926
    Prev
    Next
    INDEX
    Explanations

    negative-leaning vocabulary about the role of government and the economy.

    oai_token-act-pair · gemini-2.0-flash

    government

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    quel
    -0.48
     bar
    -0.44
     stav
    -0.44
     Conference
    -0.44
     cast
    -0.43
     CONFERENCE
    -0.43
     Facility
    -0.42
    Conference
    -0.41
    bar
    -0.41
     slik
    -0.41
    POSITIVE LOGITS
    NewReader
    0.66
     متعلقه
    0.66
    WireFormatLite
    0.64
    MethodManager
    0.64
    :✨
    0.60
    nościo
    0.60
    tvguidetime
    0.60
     resourceCulture
    0.60
     SRM
    0.59
     CharSequence
    0.59
    Activations Density 0.822%

    No Known Activations