© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2867
    Prev
    Next
    INDEX
    Explanations

    the word "Hard" and words associated with difficulty or tasks

    oai_token-act-pair · gemini-2.0-flash

    hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     hard
    -2.84
    Hard
    -2.48
     Hard
    -2.44
    hard
    -2.42
    HARD
    -2.19
     HARD
    -2.17
     harder
    -1.84
     hardest
    -1.74
     harde
    -1.66
    硬
    -1.54
    POSITIVE LOGITS
    FXMLLoader
    0.59
     poveznice
    0.57
     PARSER
    0.53
    InSection
    0.52
    !*\
    0.47
    RepeatedField
    0.47
    sizeCache
    0.47
    erals
    0.46
    เหลือ
    0.46
    HtmlAttribute
    0.46
    Activations Density 2.704%

    No Known Activations