© 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. 9920
    Prev
    Next
    INDEX
    Explanations

    words related to comparison, either words that directly indicate comparison, or words that set the stage for a comparison

    oai_token-act-pair · gemini-2.0-flash

    alling

    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
    iibo
    -0.59
     piercings
    -0.58
     dimensionless
    -0.56
     tetanus
    -0.54
     bonsai
    -0.54
     Dreamer
    -0.53
     ſeveral
    -0.52
     diſt
    -0.52
     voltmeter
    -0.52
     againſt
    -0.52
    POSITIVE LOGITS
    <bos>
    1.13
    sizeCache
    0.58
     propOrder
    0.56
    djangoproject
    0.54
     '\\;'
    0.54
     gynhyrchwyd
    0.52
    afficheront
    0.52
    ’
    0.49
    Vidite
    0.48
    tagHelperRunner
    0.47
    Activations Density 1.686%

    No Known Activations