© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10514
    Prev
    Next
    INDEX
    Explanations

    articles, numbers, and certain prepositions within otherwise technical descriptions

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Filmographie
    -0.45
    abestanden
    -0.41
     m
    -0.39
    ghty
    -0.39
    ettbewer
    -0.38
    亿元
    -0.38
    setVerticalGroup
    -0.37
     a
    -0.37
    IComponent
    -0.37
    <eos>
    -0.36
    POSITIVE LOGITS
     Theſe
    0.80
    ruptedException
    0.80
    ‍♂
    0.74
    󠁴
    0.74
     étoient
    0.73
     protoimpl
    0.73
    énéral
    0.73
     Eſ
    0.71
     iſt
    0.71
    enumi
    0.71
    Activations Density 4.049%

    No Known Activations