© 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. 5171
    Prev
    Next
    INDEX
    Explanations

    a mixed bag of terms, including geographical locations, personal pronouns, business terms and relationships.

    oai_token-act-pair · gemini-2.0-flash

    quantifiers or terms expressing quantity

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

    varied subjects

    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
    +#+#
    -1.10
    WriteTagHelper
    -0.94
    WriteAttribute
    -0.92
    InjectAttribute
    -0.91
     Roskov
    -0.88
    IUrlHelper
    -0.87
    AddField
    -0.87
    contentLoaded
    -0.85
    IsContent
    -0.83
     itſelf
    -0.82
    POSITIVE LOGITS
     plenty
    1.24
     some
    1.21
     a
    1.06
     an
    1.05
     lots
    1.03
     significant
    1.02
     considerable
    1.01
     additional
    0.98
     ample
    0.94
     no
    0.94
    Activations Density 15.753%

    No Known Activations