© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 16316
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to disclaimers and legal or research contexts, especially those involving information, consent, and accuracy.

    oai_token-act-pair · gemini-2.0-flash

    Information and research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    ÁG
    -0.67
    IALES
    -0.66
    ULUM
    -0.62
    ÉR
    -0.60
    ÁT
    -0.59
    sizeCache
    -0.59
    ÉM
    -0.57
    amel
    -0.57
    WireFormat
    -0.56
    arde
    -0.55
    POSITIVE LOGITS
     that
    0.57
     suivants
    0.57
    katapos
    0.57
     delà
    0.57
     hereof
    0.56
     bahawa
    0.54
     متعلقه
    0.54
     relating
    0.53
     antaranya
    0.53
     thats
    0.53
    Activations Density 30.029%

    No Known Activations