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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 161
    Prev
    Next
    INDEX
    Explanations

    markup and programming syntax

    oai_token-act-pair · gemini-2.0-flash

    Sep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ceptre
    -0.50
    "/></
    -0.50
    )]$
    -0.50
    ...\
    -0.49
    Rohy
    -0.48
    ...]
    -0.48
    󠁮
    -0.47
    heimer
    -0.47
     Kruger
    -0.47
    )))
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.73
    новништво
    0.65
    Források
    0.63
     PeEnEo
    0.62
     وتسجيلات
    0.61
     nahilalakip
    0.60
    تقاوى
    0.58
    TintMode
    0.57
    WithIOException
    0.54
    RUnlock
    0.51
    Activations Density 1.538%

    No Known Activations