© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3455
    Prev
    Next
    INDEX
    Explanations

    scientific language related to chemical compounds and their biological effects, particularly in the context of cancer research.

    oai_token-act-pair · gemini-2.0-flash

    terms associated with anti-cancer properties

    np_token-act-pair-logits · gpt-4o-mini

    say "anti" words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    tauchen
    -0.50
    RenderAtEndOf
    -0.49
     Signalez
    -0.47
    ymal
    -0.47
    :✨
    -0.46
     AssemblyCulture
    -0.46
    DATABASES
    -0.46
     recommandée
    -0.46
    łaszcza
    -0.45
     mxArray
    -0.45
    POSITIVE LOGITS
     tartalomajánló
    0.73
    OrBuilder
    0.66
     MatDialog
    0.59
    abestanden
    0.56
    endregion
    0.56
    antic
    0.54
    WebControls
    0.54
    úgó
    0.54
     Fides
    0.53
     Extragalactic
    0.53
    Activations Density 4.589%

    No Known Activations