© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12445
    Prev
    Next
    INDEX
    Explanations

    references to professional organizations and societies

    oai_token-act-pair · gemini-2.0-flash

    technical or organizational terms

    np_token-act-pair-logits · gpt-4o-mini

    associations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
    zuf
    -0.46
    intes
    -0.46
     richi
    -0.44
     spotlight
    -0.41
    حي
    -0.40
    phens
    -0.39
     mes
    -0.39
    Keywords
    -0.39
     bunch
    -0.38
    ms
    -0.38
    POSITIVE LOGITS
    twimg
    0.82
    CppMethod
    0.77
    ]){
    0.77
    MemoryWarning
    0.76
    FTFY
    0.75
    __':
    0.73
    adaptiveStyles
    0.73
    __":
    0.71
    SequentialGroup
    0.71
    findpost
    0.69
    Activations Density 1.387%

    No Known Activations