© 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. 7377
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns that describe people in media

    oai_token-act-pair · gemini-2.0-flash

    character/characters

    np_max-act-logits · 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
     Taktlose
    -0.69
    bleau
    -0.67
     nahilalakip
    -0.66
     ویکی‌پدی
    -0.65
    OGND
    -0.65
    +#+#
    -0.62
    ьаж
    -0.61
     CreateTagHelper
    -0.59
     estekak
    -0.59
     beginnetje
    -0.59
    POSITIVE LOGITS
     characters
    2.52
     character
    2.52
    character
    2.17
    characters
    2.09
     Character
    2.06
     Characters
    2.02
    Character
    1.95
    Characters
    1.84
     CHARACTER
    1.84
     karakter
    1.73
    Activations Density 1.673%

    No Known Activations