© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9893
    Prev
    Next
    INDEX
    Explanations

    a mix of weather and medical terms, possibly related to student health information

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     
    -0.64
     -
    -0.55
     (
    -0.50
     before
    -0.46
     $
    -0.44
     still
    -0.42
     same
    -0.41
     <
    -0.41
     sa
    -0.41
     set
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    1.15
    ArgsConstructor
    1.13
    ScopeManager
    1.08
    <bos>
    1.02
    yntaxException
    1.01
    tagHelperRunner
    1.00
    endphp
    0.99
    parsedMessage
    0.99
    ResumeLayout
    0.99
     متعلقه
    0.98
    Activations Density 0.506%

    No Known Activations