© 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. 15689
    Prev
    Next
    INDEX
    Explanations

    words or phrases that qualify a prior statement, such as 'especially', 'indeed', 'nor', or conditional clauses

    oai_token-act-pair · gemini-2.0-flash

    adverbs/conjunctions

    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
    HtmlAttribute
    -0.51
     sult
    -0.50
     Block
    -0.48
    Block
    -0.47
     block
    -0.47
    thum
    -0.46
     AssemblyProduct
    -0.45
    forte
    -0.44
     sqlite
    -0.44
     blocks
    -0.43
    POSITIVE LOGITS
    <bos>
    0.84
     <<<<<<<<<<<<<<
    0.72
     تضيفلها
    0.68
    HasForeignKey
    0.68
    PerformLayout
    0.66
    elemField
    0.61
    RectangleBorder
    0.60
     Grecs
    0.60
     légitime
    0.60
     kasarigan
    0.59
    Activations Density 2.715%

    No Known Activations