© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15999
    Prev
    Next
    INDEX
    Explanations

    song titles followed by the word "by"

    oai_token-act-pair · gemini-2.0-flash

    lists of names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     tetto
    -0.49
     
    -0.49
    iteritems
    -0.47
     My
    -0.44
    ajā
    -0.43
     s
    -0.43
    ená
    -0.42
     aient
    -0.42
     mâle
    -0.42
     ढ
    -0.42
    POSITIVE LOGITS
    
    0.98
     kasarigan
    0.91
    expandindo
    0.85
    IVEREF
    0.81
     متعلقه
    0.80
    Personendaten
    0.77
    ViewImports
    0.74
    دانشنامهٔ
    0.73
    DockStyle
    0.73
    oredCriteria
    0.71
    Activations Density 6.204%

    No Known Activations