© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11377
    Prev
    Next
    INDEX
    Explanations

    the word "the" and pronouns like our, his, and their

    oai_token-act-pair · gemini-2.0-flash

    final

    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
    Last
    -1.20
    last
    -1.16
     Last
    -1.13
     last
    -1.09
     derniers
    -0.98
     últimas
    -0.92
     LAST
    -0.92
     förra
    -0.90
     dernière
    -0.90
     últimos
    -0.88
    POSITIVE LOGITS
     final
    2.33
    final
    1.94
    Final
    1.84
     Final
    1.80
     FINAL
    1.61
    FINAL
    1.54
     finals
    0.91
     finalize
    0.89
     finales
    0.89
    finals
    0.87
    Activations Density 3.911%

    No Known Activations