© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6549
    Prev
    Next
    INDEX
    Explanations

    verbs matching contractions such as "it's", "that's", "aren't", or the word "isn't"

    oai_token-act-pair · gemini-2.0-flash

    words ending in "ly"

    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
    setVerticalGroup
    -0.82
    almost
    -0.81
     almost
    -0.79
    RenderAtEndOf
    -0.79
     Slightly
    -0.79
     TAMBIÉN
    -0.73
    Slightly
    -0.71
    Almost
    -0.71
     somewhat
    -0.71
     سكانية
    -0.70
    POSITIVE LOGITS
     necessarily
    0.91
     necessariamente
    0.82
    necessarily
    0.71
     necesariamente
    0.68
     anymore
    0.58
     sepenuhnya
    0.54
     nécessairement
    0.54
     immune
    0.53
     entirely
    0.53
     exatamente
    0.52
    Activations Density 7.848%

    No Known Activations