© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2892
    Prev
    Next
    INDEX
    Explanations

    terms related to chemistry and electricity, with some detection of water-related terms

    oai_token-act-pair · gemini-2.0-flash

    science and physics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    elemField
    -0.70
     ſta
    -0.67
     raiſ
    -0.63
    ^(@)
    -0.62
     purpoſe
    -0.60
    fjspx
    -0.58
    ++
    -0.57
     GIPHY
    -0.57
     ſtre
    -0.56
    %")
    -0.56
    POSITIVE LOGITS
     kasarigan
    0.59
     through
    0.54
    dstuk
    0.53
    AndEndTag
    0.52
    ificent
    0.52
    through
    0.52
     across
    0.52
     melalui
    0.50
    AccessorTable
    0.50
    endphp
    0.50
    Activations Density 2.984%

    No Known Activations