© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11590
    Prev
    Next
    INDEX
    Explanations

    colon separated numbers, often in the context of scientific measurements

    oai_token-act-pair · gemini-2.0-flash

    clonal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    richTextPanel
    -0.79
    MemoryWarning
    -0.74
    djangoproject
    -0.71
    sidemargin
    -0.70
    AutoresizingMask
    -0.69
    Publica
    -0.67
     Houſe
    -0.64
    клопе
    -0.63
    rrggbb
    -0.63
     $_"
    -0.63
    POSITIVE LOGITS
    <bos>
    0.49
     kele
    0.41
    瑩
    0.40
    裏
    0.40
    else
    0.39
    exo
    0.38
    Insee
    0.38
    rijk
    0.38
     fr
    0.37
     lui
    0.37
    Activations Density 0.543%

    No Known Activations