© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5657
    Prev
    Next
    INDEX
    Explanations

    descriptions of legal cases, bad personal behavior, or child abuse.

    oai_token-act-pair · gemini-2.0-flash

    engage in activities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     للمعارف
    -0.63
    KommentareTeilen
    -0.61
    Lähteet
    -0.52
     möjligt
    -0.48
     omge
    -0.44
    mnar
    -0.44
     ritorno
    -0.44
     елның
    -0.42
     fragte
    -0.42
     LUMP
    -0.41
    POSITIVE LOGITS
     activities
    0.67
     ddelweddau
    0.66
    verwijspagina
    0.65
     Rais
    0.64
    kháu
    0.64
    practices
    0.63
    activities
    0.62
    Activities
    0.62
     ACTIVITIES
    0.61
     Activities
    0.61
    Activations Density 1.669%

    No Known Activations