© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9395
    Prev
    Next
    INDEX
    Explanations

    words and phrases that relate to professionals and related fields(finance, medicine, education, marketing, forestry, law).

    oai_token-act-pair · gemini-2.0-flash

    professional roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Вікі
    -0.53
    ">//
    -0.52
    '")
    -0.47
    ')")
    -0.47
     motorists
    -0.46
    goe
    -0.46
    ücken
    -0.45
    oleic
    -0.44
    стро
    -0.44
    AMAZ
    -0.44
    POSITIVE LOGITS
    stateProvider
    0.74
    hoeddwyd
    0.68
     dataSnapshot
    0.63
     resourceCulture
    0.63
    Portale
    0.60
    ChildScrollView
    0.60
     majeurs
    0.56
    glTexCoord
    0.56
    textTheme
    0.56
    aarrggbb
    0.56
    Activations Density 8.330%

    No Known Activations