© 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. 13985
    Prev
    Next
    INDEX
    Explanations

    prepositions and other "function words" like "the", "of", "as", "to", but not pronouns.

    oai_token-act-pair · gemini-2.0-flash

    tokens related to past events or situations

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

    Extracts from longer texts

    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
     myſelf
    -1.36
     itſelf
    -1.30
     Theſe
    -1.25
     Monfieur
    -1.23
     Efq
    -1.22
    principalColumn
    -1.20
     سكانية
    -1.19
    ſelf
    -1.16
     pleaſure
    -1.16
    HtmlAttribute
    -1.15
    POSITIVE LOGITS
    e
    0.52
    sh
    0.45
     fel
    0.45
     select
    0.43
     Januar
    0.43
     
    0.43
     b
    0.43
     tra
    0.43
     Mar
    0.42
    <eos>
    0.42
    Activations Density 23.985%

    No Known Activations