© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 7695
    Prev
    Next
    INDEX
    Explanations

    content from legal documents making an argument about who owes taxes

    oai_token-act-pair · gemini-2.0-flash

    contractor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     hunne
    -0.55
     eenige
    -0.51
     sauvages
    -0.49
     fund
    -0.49
     paragraphe
    -0.49
     éto
    -0.48
     treo
    -0.48
     Fund
    -0.48
    وروبا
    -0.48
    DIPSETTING
    -0.47
    POSITIVE LOGITS
     agen
    0.74
    WaitGroup
    0.74
    CloseOperation
    0.73
     contractor
    0.69
     temp
    0.67
     CONTRACT
    0.66
    SequentialGroup
    0.65
     contractors
    0.65
     contract
    0.65
    DebuggerNonUser
    0.63
    Activations Density 0.520%

    No Known Activations