© 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. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10294
    Prev
    Next
    INDEX
    Explanations

    phrases about helping one stay or keep a certain way

    oai_token-act-pair · gemini-2.0-flash

    staying safe and updated

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     resourceCulture
    -0.85
    berdayakan
    -0.80
     myſelf
    -0.78
     himſelf
    -0.74
     Jefus
    -0.74
    iastes
    -0.71
     itſelf
    -0.69
     kaarangay
    -0.67
     disambiguazione
    -0.67
     themſelves
    -0.66
    POSITIVE LOGITS
     cie
    0.54
    lika
    0.48
     li
    0.46
     clean
    0.44
     Prime
    0.44
    节
    0.43
     lifted
    0.42
    พ
    0.41
     чи
    0.40
    節
    0.40
    Activations Density 0.956%

    No Known Activations