© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12967
    Prev
    Next
    INDEX
    Explanations

    sentences describing lab methods and materials in molecular biology

    oai_token-act-pair · gemini-2.0-flash

    gene expression in scientific publication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     sessile
    -0.51
     bonté
    -0.51
     quæ
    -0.50
     péché
    -0.50
     חיצוניים
    -0.50
     ganglia
    -0.50
     consentement
    -0.50
     asupra
    -0.49
     handker
    -0.49
    InSection
    -0.49
    POSITIVE LOGITS
    tagHelperRunner
    0.70
     تانيه
    0.57
    ReusableCell
    0.56
     DialogInterface
    0.56
     يتيمه
    0.54
     JpaRepository
    0.54
    roe
    0.52
    mockito
    0.51
     GenerationType
    0.50
    npos
    0.48
    Activations Density 4.961%

    No Known Activations