© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6549
    Prev
    Next
    INDEX
    Explanations

    the word "and" along with miscellaneous other words.

    oai_token-act-pair · gemini-2.0-flash

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     iprot
    -0.67
    IBOutlet
    -0.64
    prepareStatement
    -0.63
    tagHelperRunner
    -0.63
    ########.
    -0.62
    copg
    -0.55
    orteur
    -0.55
     voltmeter
    -0.53
     שוליים
    -0.53
     NSCoder
    -0.52
    POSITIVE LOGITS
    sizeCache
    0.57
     кӀ
    0.56
    ardless
    0.52
    StoreMessageInfo
    0.52
    glMatrixMode
    0.51
    grunns
    0.50
    /***/
    0.50
     ExecuteAsync
    0.48
    nard
    0.48
    iterranean
    0.48
    Activations Density 2.723%

    No Known Activations