© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1435
    Prev
    Next
    INDEX
    Explanations

    the word "small" with varying capitalization and surrounding context.

    oai_token-act-pair · gemini-2.0-flash

    small

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     Wayback
    -0.55
    CodeAttribute
    -0.51
     Réalisation
    -0.49
     насељу
    -0.48
    اق
    -0.47
    lump
    -0.47
    BindingSource
    -0.46
    ous
    -0.46
     Existe
    -0.45
     mates
    -0.45
    POSITIVE LOGITS
     MainAxisSize
    0.57
    :✨
    0.57
    fromnode
    0.55
    تقاوى
    0.51
     skrift
    0.49
     feinen
    0.49
     Walkover
    0.49
    valget
    0.48
    assies
    0.48
    География
    0.48
    Activations Density 2.106%

    No Known Activations