© 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. 11067
    Prev
    Next
    INDEX
    Explanations

    phrases indicating someone is considered important or well-regarded

    oai_token-act-pair · gemini-2.0-flash

    privilege/honored

    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
     reappeared
    -0.43
     reappear
    -0.40
     disappears
    -0.38
     terjun
    -0.36
    rusty
    -0.36
     replaced
    -0.36
    ęż
    -0.36
    RenderAtEndOf
    -0.35
     disappeared
    -0.34
     Replaced
    -0.34
    POSITIVE LOGITS
    expandindo
    0.88
     BoxFit
    0.72
     StatefulWidget
    0.71
    HasForeignKey
    0.70
     noqa
    0.69
     كومونز
    0.68
     snippetHide
    0.65
     saites
    0.64
    saraba
    0.63
     OMITBAD
    0.63
    Activations Density 0.633%

    No Known Activations