© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12478
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uniqueness or limitation

    oai_token-act-pair · gemini-2.0-flash

    only, one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ForValue
    -0.54
    fully
    -0.54
    ⓧ
    -0.54
    offsetof
    -0.52
     aceea
    -0.50
     pourrez
    -0.49
     lesquels
    -0.49
    Fully
    -0.48
    HtmlAttribute
    -0.48
     misalnya
    -0.48
    POSITIVE LOGITS
    tvguidetime
    0.91
    脚注の使い方
    0.81
    rungsseite
    0.59
     StatelessWidget
    0.57
    \{\\
    0.56
     OnInit
    0.54
     StatefulWidget
    0.53
    #+#
    0.53
     initComponents
    0.53
    onton
    0.52
    Activations Density 1.783%

    No Known Activations