© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3281
    Prev
    Next
    INDEX
    Explanations

    words or phrases indicating a numerical decrease

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Efq
    -0.90
     itſelf
    -0.85
     myſelf
    -0.80
     ſtate
    -0.80
     initComponents
    -0.79
     themſelves
    -0.78
     ſche
    -0.78
    +#+
    -0.77
    BagConstraints
    -0.77
    avadoc
    -0.77
    POSITIVE LOGITS
    5
    0.50
    4
    0.49
    0
    0.48
    dep
    0.47
    1
    0.46
    ś
    0.46
    readystatechange
    0.45
    getResultList
    0.45
    Cor
    0.44
    c
    0.44
    Activations Density 1.663%

    No Known Activations