© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13643
    Prev
    Next
    INDEX
    Explanations

    words, especially adjectives, that add detail to a description.

    oai_token-act-pair · gemini-2.0-flash

    language and communication

    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
     resourceCulture
    -1.05
    ⓧ
    -1.01
     autorytatywna
    -0.98
    abestanden
    -0.95
    Hochspringen
    -0.90
    
    -0.89
     betweenstory
    -0.87
    WebVitals
    -0.86
    SourceChecksum
    -0.85
     CreateTagHelper
    -0.83
    POSITIVE LOGITS
     infatti
    0.44
     must
    0.40
     "]";
    0.38
     totiž
    0.37
     portata
    0.36
     le
    0.35
     concentración
    0.35
    ]`
    0.35
    cisco
    0.34
     amp
    0.34
    Activations Density 1.488%

    No Known Activations