© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    occurrences of the pronoun "she"

    oai_token-act-pair · gemini-2.0-flash

    book passages

    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
    InteropServices
    -0.50
    SES
    -0.48
     الحره
    -0.48
    furter
    -0.48
    setof
    -0.46
     Then
    -0.46
     lenker
    -0.45
    Sure
    -0.44
    SPI
    -0.44
     بتاريخ
    -0.44
    POSITIVE LOGITS
    ConstraintMaker
    0.75
    eseorang
    0.69
     élu
    0.62
     insuffisamment
    0.57
     AppColors
    0.56
     cherchés
    0.55
    amaño
    0.55
    dyž
    0.55
    enumi
    0.54
     Infórmanos
    0.54
    Activations Density 2.842%

    No Known Activations