© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5169
    Prev
    Next
    INDEX
    Explanations

    terms related to finance and investment

    oai_token-act-pair · gemini-2.0-flash

    management

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    vistar
    -0.54
    enoid
    -0.53
    ressum
    -0.53
    joined
    -0.52
     continúas
    -0.51
    adze
    -0.50
     conseille
    -0.49
    onghi
    -0.49
    ofollow
    -0.47
    urati
    -0.47
    POSITIVE LOGITS
     ModelExpression
    0.65
     TestBed
    0.63
    enterOuterAlt
    0.62
     JpaRepository
    0.56
    stdc
    0.56
     memoized
    0.56
     '\\;'
    0.55
     ActionResult
    0.55
     ExecuteAsync
    0.54
    хьтан
    0.53
    Activations Density 22.701%

    No Known Activations