© 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. 8948
    Prev
    Next
    INDEX
    Explanations

    technical writing in scientific or research publications, possibly related to medical topics, networks, or physics

    oai_token-act-pair · gemini-2.0-flash

    is

    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
    étoit
    -0.74
    RTLR
    -0.68
    tagHelperRunner
    -0.68
    "])
    -0.66
     Мексичка
    -0.66
     navigateur
    -0.66
    !")
    -0.65
    "]]
    -0.65
    ']")
    -0.64
    +#+#
    -0.63
    POSITIVE LOGITS
     propel
    0.58
     escal
    0.57
     bol
    0.56
     push
    0.52
     stiffened
    0.51
     dashed
    0.50
    Push
    0.48
    成
    0.48
     weighing
    0.47
     indirec
    0.47
    Activations Density 12.947%

    No Known Activations