© 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. 14225
    Prev
    Next
    INDEX
    Explanations

    pronouns and contractions

    oai_token-act-pair · 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
    SourceChecksum
    -0.79
     Anſ
    -0.78
     ſtand
    -0.77
    Hentet
    -0.77
     Monfieur
    -0.75
     houſe
    -0.73
     Houſe
    -0.73
     doubtnut
    -0.70
     purpoſe
    -0.69
     itſelf
    -0.69
    POSITIVE LOGITS
    しまった
    0.46
    基
    0.45
    伍
    0.43
     cabo
    0.41
    SharedDtor
    0.41
     surla
    0.38
     Swal
    0.38
     consulter
    0.37
    chede
    0.37
     Familienname
    0.37
    Activations Density 2.650%

    No Known Activations