© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13060
    Prev
    Next
    INDEX
    Explanations

    the stem "har" in words, possibly related to "harrier" birds

    oai_token-act-pair · gemini-2.0-flash

    har

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Har
    -2.47
     Har
    -2.45
     har
    -2.45
    har
    -2.38
    HAR
    -1.98
     HAR
    -1.97
     Harbour
    -1.06
     Хар
    -1.05
     هار
    -1.03
    ahar
    -1.02
    POSITIVE LOGITS
    IntoConstraints
    1.07
    expandindo
    0.81
     يتيمه
    0.79
    AlterField
    0.76
    createCanvas
    0.70
     nahilalakip
    0.67
     IBOutlet
    0.65
    ticides
    0.63
    AccessFile
    0.63
     Cater
    0.62
    Activations Density 0.689%

    No Known Activations