© 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
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9085
    Prev
    Next
    INDEX
    Explanations

    statements acknowledging contributions

    oai_token-act-pair · gemini-2.0-flash

    Acknowledgements and thank yous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    󠁿
    -0.63
    voorbeeld
    -0.58
    portál
    -0.58
    存于互联网档案馆
    -0.57
    Hentet
    -0.54
    liceerd
    -0.54
    Alike
    -0.54
    ynb
    -0.54
    Cue
    -0.52
     مشين
    -0.51
    POSITIVE LOGITS
    UnsafeEnabled
    0.58
    addCriterion
    0.57
    ंदीखरीदारी
    0.52
     Вікіпе
    0.50
    RTSN
    0.50
    ContentAsync
    0.49
     consigo
    0.49
    WebVitals
    0.47
     olma
    0.47
    ίσ
    0.45
    Activations Density 5.721%

    No Known Activations