© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2242
    Prev
    Next
    INDEX
    Explanations

    language from poems or songs

    oai_token-act-pair · gemini-2.0-flash

    Dark poetry/lyrics

    np_max-act-logits · gemini-2.0-flash

    word-start

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    UnsafeEnabled
    -0.71
    WarningLevel
    -0.69
    RegressionTest
    -0.65
     الحره
    -0.62
    脚注の使い方
    -0.62
    Datuak
    -0.61
    
    -0.61
     CWE
    -0.60
    تقاوى
    -0.59
     שוליים
    -0.59
    POSITIVE LOGITS
     señor
    0.48
     Unto
    0.47
     unto
    0.46
    .’
    0.44
     hath
    0.43
     shameless
    0.42
    );*/
    0.42
     necessariamente
    0.42
    ,’
    0.42
     ’
    0.42
    Activations Density 41.114%

    No Known Activations