© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15559
    Prev
    Next
    INDEX
    Explanations

    measurements of frequency over time

    oai_token-act-pair · gemini-2.0-flash

    time-related rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     Shakspeare
    -0.62
    WaitGroup
    -0.61
    StructEnd
    -0.60
     Efq
    -0.58
     doInBackground
    -0.58
    .*")]
    -0.58
     gră
    -0.58
    endpush
    -0.55
     Konzentration
    -0.55
     *)&
    -0.54
    POSITIVE LOGITS
    Personendaten
    0.66
    matchCondition
    0.49
     para
    0.48
    ADUATE
    0.47
    Thiết
    0.46
    LLES
    0.46
    licopter
    0.46
    knecht
    0.44
    лизм
    0.43
    irability
    0.43
    Activations Density 16.280%

    No Known Activations