© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14216
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns being or having an experience.

    oai_token-act-pair · gemini-2.0-flash

    narrative text

    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
    Negative Logits
    ARROLL
    -0.54
     AssemblyVersion
    -0.48
    رضا
    -0.45
     SearchView
    -0.44
     נס
    -0.44
     risa
    -0.43
    giphy
    -0.43
     pères
    -0.42
     åt
    -0.41
     прико
    -0.41
    POSITIVE LOGITS
     gynhyrchwyd
    0.73
     AssemblyCulture
    0.69
    GraphicsUnit
    0.68
    Hentet
    0.65
    الإنجليزية
    0.63
    AndEndTag
    0.62
    }}$\\
    0.61
    ')));
    0.61
     bParam
    0.61
    HtmlAttribute
    0.60
    Activations Density 2.792%

    No Known Activations