© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8394
    Prev
    Next
    INDEX
    Explanations

    words related to thanking people and also the word "relational"

    oai_token-act-pair · gemini-2.0-flash

    research acknowledgements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    <bos>
    -0.63
    »
    -0.52
    بل
    -0.50
     all
    -0.49
     for
    -0.48
    —
    -0.48
     Fre
    -0.48
     St
    -0.48
    <eos>
    -0.47
     Mar
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    1.36
    Personendaten
    1.30
    AndEndTag
    1.30
    GEBURTSDATUM
    1.13
    MessageTagHelper
    1.11
     pleaſure
    1.05
    脚注の使い方
    1.02
    protoimpl
    1.02
     disambiguazione
    1.01
    RegistryLite
    1.00
    Activations Density 0.033%

    No Known Activations