© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 6251
    Prev
    Next
    INDEX
    Explanations

    lines from rap songs

    oai_token-act-pair · gemini-2.0-flash

    ending with "ning" sounds

    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
    Jîn
    -0.76
    المناصب
    -0.74
    ftagPool
    -0.68
    Autoritní
    -0.68
    complexContent
    -0.67
    MessageOf
    -0.65
    InjectAttribute
    -0.62
     resourceCulture
    -0.61
    BeginContext
    -0.58
    abestanden
    -0.58
    POSITIVE LOGITS
    ned
    0.60
    ning
    0.58
    NING
    0.57
    ny
    0.57
    ne
    0.57
    ni
    0.55
    ded
    0.54
    na
    0.54
    ner
    0.54
    net
    0.54
    Activations Density 4.909%

    No Known Activations