© 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. 13989
    Prev
    Next
    INDEX
    Explanations

    terms related to genetic analysis and manipulation

    oai_token-act-pair · gemini-2.0-flash

    Biology/Genetics text

    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
     >=",
    -0.90
     Савезне
    -0.77
    OGND
    -0.77
     مرئيه
    -0.74
     maîtres
    -0.72
     initComponents
    -0.69
    protoimpl
    -0.69
    fitriones
    -0.67
     enfans
    -0.66
     étoit
    -0.66
    POSITIVE LOGITS
    TargetException
    0.42
    ArrowToggle
    0.40
    вления
    0.35
    ém
    0.35
    سیون
    0.35
    astic
    0.34
    om
    0.34
    anik
    0.33
    Variable
    0.33
    idase
    0.33
    Activations Density 2.983%

    No Known Activations