© 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. 5177
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs and personal pronouns.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word "achieve"

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

    achievement

    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
    Diweddarwch
    -0.87
    ScopeManager
    -0.84
     financières
    -0.83
     fermés
    -0.82
    ंदीखरीदारी
    -0.78
    Geplaatst
    -0.77
     avoient
    -0.74
     normaux
    -0.73
    verwijspagina
    -0.72
     étoient
    -0.71
    POSITIVE LOGITS
     achieve
    1.92
     achieved
    1.88
     achieves
    1.86
     achieving
    1.77
    Achie
    1.68
     Achieve
    1.63
    achieve
    1.62
     achievement
    1.61
     Achieving
    1.54
    achieved
    1.53
    Activations Density 2.507%

    No Known Activations