© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10628
    Prev
    Next
    INDEX
    Explanations

    sentences with personal pronouns, especially "we" and "I", possibly related to making promises or statements.

    oai_token-act-pair · gemini-2.0-flash

    we or 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_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    Willing
    -0.57
    
    -0.52
     незавершена
    -0.52
    <%@
    -0.51
    stdc
    -0.50
    <bos>
    -0.50
    xically
    -0.50
     Paglinawan
    -0.49
     Sui
    -0.49
    RenderAtEndOf
    -0.49
    POSITIVE LOGITS
     share
    0.75
    setVerticalGroup
    0.69
    share
    0.67
     Share
    0.62
    queryInterface
    0.60
    MessageTagHelper
    0.58
    SHARE
    0.57
    nościo
    0.56
    Share
    0.55
     SHARE
    0.54
    Activations Density 3.448%

    No Known Activations