© 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. 11680
    Prev
    Next
    INDEX
    Explanations

    words and numbers used when offering advice

    oai_token-act-pair · gemini-2.0-flash

    Code/Questions

    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
     EnglishChoose
    -0.62
     éto
    -0.60
     lehe
    -0.59
     chré
    -0.59
     obé
    -0.58
    ppure
    -0.57
     vœ
    -0.57
     gerecht
    -0.57
    berdayakan
    -0.56
    offrir
    -0.54
    POSITIVE LOGITS
    MockBean
    0.63
    CloseOperation
    0.59
    Composable
    0.54
     Metab
    0.52
    epam
    0.52
    ModelBuilder
    0.51
     size
    0.50
    aarrggbb
    0.49
     temp
    0.48
     metab
    0.47
    Activations Density 5.813%

    No Known Activations