© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12367
    Prev
    Next
    INDEX
    Explanations

    opinions, particularly ones that are contentious or extreme

    oai_token-act-pair · gemini-2.0-flash

    argumentative texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     يتيمه
    -0.99
    Personendaten
    -0.98
    rungsseite
    -0.96
    __':
    -0.92
     незавершена
    -0.92
     متعلقه
    -0.91
    InjectAttribute
    -0.86
    NameInMap
    -0.84
    ніципалі
    -0.82
    parsedMessage
    -0.82
    POSITIVE LOGITS
     ngang
    0.53
     new
    0.43
    stra
    0.42
    canestro
    0.41
     Zeitpunkt
    0.41
     b
    0.41
     जाना
    0.41
    堪
    0.41
    歇
    0.40
    !
    0.40
    Activations Density 1.306%

    No Known Activations