© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12460
    Prev
    Next
    INDEX
    Explanations

    the word "step" followed by a positive adjective

    oai_token-act-pair · gemini-2.0-flash

    step

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     للمعارف
    -1.02
    ReusableCell
    -0.87
    ſelf
    -0.84
     myſelf
    -0.82
     purpoſe
    -0.81
    ſelves
    -0.79
     preſent
    -0.78
     itſelf
    -0.75
     reaſon
    -0.75
     ſever
    -0.75
    POSITIVE LOGITS
    child
    0.46
     devrez
    0.40
     nødvendig
    0.40
     BY
    0.39
    도록
    0.39
     semula
    0.38
     noodzake
    0.37
     preocupar
    0.36
    abá
    0.36
    Count
    0.36
    Activations Density 1.327%

    No Known Activations