© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6008
    Prev
    Next
    INDEX
    Explanations

    numbers containing a comma

    oai_token-act-pair · gemini-2.0-flash

    Statistics and 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_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     proportion
    -1.02
    proportion
    -0.94
    propor
    -0.94
     Proportion
    -0.93
     proportional
    -0.91
     Propor
    -0.90
     propor
    -0.90
     proportions
    -0.86
    Proportion
    -0.85
     proportionality
    -0.84
    POSITIVE LOGITS
    ile
    0.48
    יח
    0.47
     Comments
    0.46
    cri
    0.43
    ed
    0.43
    cell
    0.43
    лист
    0.42
    iaus
    0.42
    blis
    0.42
     tunggal
    0.41
    Activations Density 0.265%

    No Known Activations