© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3582
    Prev
    Next
    INDEX
    Explanations

    phrases like "contact us" or other medical/business related offerings

    oai_token-act-pair · gemini-2.0-flash

    call to action/medical advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     للمعارف
    -0.69
    (!__
    -0.66
     Vikipedi
    -0.65
    MessageOf
    -0.64
    </thead>
    -0.64
    <bos>
    -0.63
    __.__
    -0.63
    Autoritní
    -0.63
    GeneratedCode
    -0.60
     AssemblyTitle
    -0.60
    POSITIVE LOGITS
     contact
    0.47
    ToListAsync
    0.46
    Contact
    0.45
     nifer
    0.45
    hasErrors
    0.44
    vités
    0.44
    asable
    0.43
     suivants
    0.43
    Space
    0.42
     ljus
    0.42
    Activations Density 1.130%

    No Known Activations