© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13202
    Prev
    Next
    INDEX
    Explanations

    words that appear to be associated with politics, contracts, and numbers.

    oai_token-act-pair · gemini-2.0-flash

    News/Articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    Additionally
    -0.78
     Additionally
    -0.77
    TLDR
    -0.69
     Regardless
    -0.66
     comedic
    -0.65
    Regardless
    -0.64
    rader
    -0.61
    redacted
    -0.59
     referencing
    -0.59
     overarching
    -0.59
    POSITIVE LOGITS
     daß
    0.73
    ')}}
    0.66
    цездатний
    0.65
     muß
    0.64
     läßt
    0.63
    الحياه
    0.63
     समीक्षक
    0.61
    "])
    0.58
    ]")]
    0.58
    KURZBESCHREIBUNG
    0.58
    Activations Density 4.471%

    No Known Activations