© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13252
    Prev
    Next
    INDEX
    Explanations

    the word "birth" and sometimes intensifiers like "too" or "really"

    oai_token-act-pair · gemini-2.0-flash

    birth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ValueStyle
    -0.83
    protoc
    -0.69
     demais
    -0.63
    Autoritní
    -0.59
     compounds
    -0.57
    AddTagHelper
    -0.55
    estero
    -0.55
    êmio
    -0.55
     demás
    -0.54
    Revenir
    -0.54
    POSITIVE LOGITS
    fjspx
    0.71
     Numerade
    0.67
    DrawerToggle
    0.66
     bespoke
    0.66
     rucksack
    0.57
     localised
    0.57
    Rüyada
    0.54
     transférez
    0.54
     claust
    0.54
     Lancashire
    0.54
    Activations Density 0.268%

    No Known Activations