© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4611
    Prev
    Next
    INDEX
    Explanations

    autobiographical or biographical statements about someone's upbringing and education.

    oai_token-act-pair · gemini-2.0-flash

    growing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    kezik
    -0.52
    PDOException
    -0.47
    BeginContext
    -0.46
    ulator
    -0.45
    reurs
    -0.44
     ringan
    -0.43
     wipers
    -0.42
     couple
    -0.41
    olisme
    -0.41
     vas
    -0.41
    POSITIVE LOGITS
     growing
    1.24
    Growing
    1.17
     Growing
    1.16
    growing
    1.09
     GROW
    1.01
     grow
    0.98
     grows
    0.95
     grew
    0.91
    GROW
    0.90
     grown
    0.89
    Activations Density 3.765%

    No Known Activations