© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2136
    Prev
    Next
    INDEX
    Explanations

    terms related to disease and genetics.

    oai_token-act-pair · gemini-2.0-flash

    biology/genetics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ReusableCell
    -0.80
     esternos
    -0.75
    ⓧ
    -0.70
    afficheront
    -0.70
    AccessorTable
    -0.66
    extAlignment
    -0.65
    fjspx
    -0.63
    IntoConstraints
    -0.63
    Попис
    -0.63
     насељу
    -0.62
    POSITIVE LOGITS
    Counters
    0.47
    encers
    0.43
     life
    0.43
    Factor
    0.43
     कह
    0.43
     vänt
    0.43
     møte
    0.42
    ("")]
    0.41
     Thad
    0.41
    anel
    0.41
    Activations Density 0.892%

    No Known Activations