© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5841
    Prev
    Next
    INDEX
    Explanations

    the word "children" and words synonymous for bad things that can happen.

    oai_token-act-pair · gemini-2.0-flash

    adverse events and children

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.59
    ıdır
    -0.52
    Getter
    -0.49
    EXCEPT
    -0.47
    otex
    -0.46
    providedIn
    -0.46
     cdi
    -0.45
    ↵↵
    -0.45
     Wettbewer
    -0.44
    Many
    -0.44
    POSITIVE LOGITS
    ########.
    0.80
     gynhyrchwyd
    0.78
     تضيفلها
    0.77
     дописавши
    0.73
     ddelweddau
    0.73
     Мексичка
    0.72
    adaptiveStyles
    0.72
     препратки
    0.72
     Normdatei
    0.71
     arşivlendi
    0.69
    Activations Density 0.295%

    No Known Activations