© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12515
    Prev
    Next
    INDEX
    Explanations

    language related to debt and legal action

    oai_token-act-pair · gemini-2.0-flash

    Debt collection/seizing assets

    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
     bribe
    -0.51
    TableCell
    -0.49
     bribery
    -0.48
     king
    -0.45
    onViewCreated
    -0.44
    setCustom
    -0.44
    ©
    -0.43
     secret
    -0.42
     évaluations
    -0.41
     bribes
    -0.41
    POSITIVE LOGITS
    StreetMap
    0.78
    Personensuche
    0.73
    HtmlAttribute
    0.66
    TestingModule
    0.65
     AssemblyTitle
    0.65
    tvguidetime
    0.63
     nationaux
    0.60
    IntoConstraints
    0.59
     fermés
    0.59
     AssemblyCompany
    0.58
    Activations Density 0.731%

    No Known Activations