© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9132
    Prev
    Next
    INDEX
    Explanations

    conjunctions, especially the word 'and', followed by a punctuation mark or a personal pronoun like I

    oai_token-act-pair · gemini-2.0-flash

    And

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    /
    -0.96
     /
    -0.61
     and
    -0.61
    そして
    -0.55
    Then
    -0.51
    then
    -0.50
    /";
    -0.50
    .
    -0.48
    和
    -0.47
     &
    -0.47
    POSITIVE LOGITS
    RenderAtEndOf
    0.80
     utafitiHapana
    0.77
    出版年
    0.68
    AILABLE
    0.65
    ſelves
    0.64
     Majefty
    0.63
    ConverterFactory
    0.63
     Jefus
    0.62
    ENEZ
    0.61
    ratulations
    0.60
    Activations Density 2.842%

    No Known Activations