© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14281
    Prev
    Next
    INDEX
    Explanations

    the word "Hi", sometimes with other contextual words like "-" or "_"

    oai_token-act-pair · gemini-2.0-flash

    text with high frequency of "Hi"

    np_token-act-pair-logits · gpt-4o-mini

    hi

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     تانيه
    -0.65
     发表于
    -0.52
    ровок
    -0.47
     Lug
    -0.45
    hésite
    -0.43
    州市
    -0.43
    lahoma
    -0.43
    lagen
    -0.43
    inage
    -0.43
    도록
    -0.43
    POSITIVE LOGITS
     Италијани
    0.68
    GeneratedCode
    0.60
    AnimationsModule
    0.59
    شهاد
    0.59
    tvguidetime
    0.58
     initComponents
    0.55
    ackerel
    0.54
    Према
    0.54
     ComVisible
    0.54
    PreferredItem
    0.54
    Activations Density 0.279%

    No Known Activations