© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1758
    Prev
    Next
    INDEX
    Explanations

    words related to hyacinths, particularly grape hyacinths, their planting, and care

    oai_token-act-pair · gemini-2.0-flash

    plant growth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    GEBURTSDATUM
    -0.73
    KEYCODE
    -0.69
    abestanden
    -0.66
    Dữ
    -0.65
    Datuak
    -0.65
     saucer
    -0.63
    Hauptartikel
    -0.63
    GIVEREF
    -0.63
    expandindo
    -0.61
    IndentedString
    -0.60
    POSITIVE LOGITS
    allis
    0.47
     Hillsborough
    0.46
     grass
    0.43
    asons
    0.43
    CRIP
    0.42
    BCF
    0.42
     stol
    0.41
     Blumen
    0.41
     bottes
    0.41
    мә
    0.40
    Activations Density 0.813%

    No Known Activations