© 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. 2509
    Prev
    Next
    INDEX
    Explanations

    the letter "i" followed by a period, especially in the context of "i.e."

    oai_token-act-pair · gemini-2.0-flash

    the first person singular pronoun "I"

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

    i

    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
    UrlResolution
    -0.77
     jScrollPane
    -0.61
    ThemeOverlay
    -0.60
    #+#
    -0.60
    apimachinery
    -0.60
     CGPoint
    -0.58
    MergeFrom
    -0.55
    Datuak
    -0.55
     Meksiku
    -0.54
    basicConfig
    -0.54
    POSITIVE LOGITS
     médic
    0.46
     poésie
    0.45
    tymologie
    0.45
     arché
    0.45
    minster
    0.45
     églises
    0.42
    Zum
    0.42
    سياسي
    0.42
    mybatisplus
    0.41
     inom
    0.41
    Activations Density 0.646%

    No Known Activations