© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 406
    Prev
    Next
    INDEX
    Explanations

    words or word fragments referring to heroic roles or jobs

    oai_token-act-pair · gemini-2.0-flash

    hero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     viewDidLoad
    -0.75
    SequentialGroup
    -0.74
    WithIOException
    -0.72
    migrationBuilder
    -0.72
     Walkover
    -0.70
     MainAxisSize
    -0.66
     Exacts
    -0.66
    Slf
    -0.65
    脚注の使い方
    -0.63
    httphttps
    -0.63
    POSITIVE LOGITS
    <bos>
    0.73
     heroes
    0.56
    Heroes
    0.51
     hero
    0.51
    cdef
    0.50
     geldig
    0.50
     héroes
    0.49
    HERO
    0.49
    Proteins
    0.49
    heroes
    0.48
    Activations Density 0.761%

    No Known Activations