© 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. 10170
    Prev
    Next
    INDEX
    Explanations

    CSS class names related to column size

    oai_token-act-pair · gemini-2.0-flash

    md

    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
    md
    -0.75
     sm
    -0.67
    sm
    -0.63
     estekak
    -0.60
    SequentialGroup
    -0.59
    medim
    -0.56
     Sm
    -0.54
     md
    -0.52
     trữ
    -0.52
    存于互联网档案馆
    -0.52
    POSITIVE LOGITS
    Personendaten
    0.65
    ftagPool
    0.58
     CURIAM
    0.56
     configureStore
    0.54
    кисло
    0.54
    ebabkan
    0.54
    AndEndTag
    0.53
    "])
    0.52
    iega
    0.52
     समीक्षाओं
    0.52
    Activations Density 0.904%

    No Known Activations