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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 10291
    Prev
    Next
    INDEX
    Explanations

    words and symbols commonly found in scientific abstracts that describe the chemical make up of organic compounds

    oai_token-act-pair · gemini-2.0-flash

    apostrophes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    ionView
    -0.50
     Pelop
    -0.49
     getArguments
    -0.48
    =$?
    -0.48
     Judson
    -0.47
    ARGUMENT
    -0.47
    ocor
    -0.46
    żer
    -0.46
     '*')
    -0.45
    ITest
    -0.45
    POSITIVE LOGITS
     Normdatei
    0.70
    OGND
    0.67
    ouwd
    0.57
     snippetHide
    0.57
    Sucesor
    0.56
     كومونز
    0.55
     estekak
    0.53
    enterOuterAlt
    0.52
    heden
    0.51
    herited
    0.51
    Activations Density 2.577%

    No Known Activations