© 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. 15636
    Prev
    Next
    INDEX
    Explanations

    numbers, math operations, or codes

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
    <eos>
    -0.50
     he
    -0.48
     war
    -0.44
     ma
    -0.42
    Mode
    -0.42
     dou
    -0.41
     ta
    -0.40
     (
    -0.40
    ipun
    -0.40
     
    -0.39
    POSITIVE LOGITS
     itſelf
    1.02
     myſelf
    0.93
    RenderAtEndOf
    0.92
     Shakspeare
    0.90
    <bos>
    0.87
     MainAxisSize
    0.85
     للمعارف
    0.82
     Monfieur
    0.81
     فريبيس
    0.81
     becauſe
    0.81
    Activations Density 38.303%

    No Known Activations