© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3333
    Prev
    Next
    INDEX
    Explanations

    words in sentences describing metaphorical or literal prominence, brightness, or visibility.

    oai_token-act-pair · gemini-2.0-flash

    words related to brightness

    np_token-act-pair-logits · gpt-4o-mini

    brightness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ftagPool
    -0.56
    Personendaten
    -0.55
     CreateTagHelper
    -0.52
    تقاوى
    -0.51
     getItemCount
    -0.51
     désolés
    -0.50
    rzost
    -0.49
    AntiForgeryToken
    -0.47
     movimenti
    -0.47
    prefixer
    -0.47
    POSITIVE LOGITS
     bright
    1.27
     brightness
    1.21
    bright
    1.19
     brightest
    1.16
    brightness
    1.10
     Bright
    1.09
     brighter
    1.08
     BRIGHT
    1.08
     shine
    1.05
     shining
    1.05
    Activations Density 1.492%

    No Known Activations