© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9935
    Prev
    Next
    INDEX
    Explanations

    articles about general philosophical or scientific concepts and facts

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     iſt
    -0.73
    NUMX
    -0.64
     confronti
    -0.64
     ―――――
    -0.63
    ſelf
    -0.63
     Jefus
    -0.63
     itſelf
    -0.62
    bbero
    -0.60
    ſelves
    -0.60
     gettyimages
    -0.60
    POSITIVE LOGITS
    GOTREF
    0.70
     esternos
    0.56
     متعلقه
    0.55
    Havolalar
    0.55
    wikidata
    0.49
     pageContext
    0.48
    od
    0.46
    o
    0.45
    gg
    0.44
     res
    0.44
    Activations Density 2.831%

    No Known Activations