© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6417
    Prev
    Next
    INDEX
    Explanations

    Hawaiian words and phrases

    oai_token-act-pair · gemini-2.0-flash

    foreign or uncommon terms

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

    Hawaii/Hawaiian/Polynesian

    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
     Arm
    -0.39
    ARA
    -0.38
     T
    -0.37
     memory
    -0.36
    Yet
    -0.35
    嗦
    -0.35
     ny
    -0.35
     arm
    -0.35
    grat
    -0.35
     twarzy
    -0.35
    POSITIVE LOGITS
     كومونز
    0.95
    ValueStyle
    0.85
    Vidite
    0.81
     ReactDOM
    0.79
    saraba
    0.75
     disambiguazione
    0.74
     Normdatei
    0.70
    IBarButtonItem
    0.70
     Wiktionnaire
    0.69
    下载附件
    0.69
    Activations Density 1.098%

    No Known Activations