© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7323
    Prev
    Next
    INDEX
    Explanations

    the phrase "Alle musikstykker" which likely means "All music"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     drums
    -0.44
    proteins
    -0.42
    pakah
    -0.42
    iale
    -0.41
     weeds
    -0.41
     scouts
    -0.40
     ghosts
    -0.40
    markets
    -0.40
    iniums
    -0.40
    fahrens
    -0.39
    POSITIVE LOGITS
    Personendaten
    1.08
    AddHtmlAttribute
    0.94
    +#+#
    0.85
    تقاوى
    0.79
     onPostExecute
    0.77
    Diwedd
    0.74
    AndEndTag
    0.73
    TagMode
    0.71
    PreferredItem
    0.67
    AddTagHelper
    0.66
    Activations Density 0.175%

    No Known Activations