© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 16269
    Prev
    Next
    INDEX
    Explanations

    mentions of the private sector combined with words that describe it like "government", "hospital", "agency", "prison", or "health"

    oai_token-act-pair · gemini-2.0-flash

    private

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    apimachinery
    -0.71
     Roskov
    -0.64
     виправивши
    -0.59
    ntax
    -0.57
    protoimpl
    -0.53
    spira
    -0.51
    imath
    -0.51
    chymal
    -0.50
    hoeddwyd
    -0.50
    adah
    -0.47
    POSITIVE LOGITS
    TagMode
    0.60
    XMLSchema
    0.47
     capitalized
    0.46
    AutoresizingMask
    0.46
     capitals
    0.46
     capital
    0.46
    ابی
    0.46
    quese
    0.44
     recto
    0.44
    moveToFirst
    0.43
    Activations Density 4.508%

    No Known Activations