© 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. 3359
    Prev
    Next
    INDEX
    Explanations

    information surrounding a crime, especially murder

    oai_token-act-pair · gemini-2.0-flash

    death, loss

    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
    脚注の使い方
    -0.84
    NewUrlParser
    -0.82
    NameInMap
    -0.79
    ]")]
    -0.79
     ExecuteAsync
    -0.73
    Personendaten
    -0.72
    auré
    -0.71
    rungsseite
    -0.71
    WriteAttribute
    -0.70
    IContainer
    -0.70
    POSITIVE LOGITS
     died
    0.54
     spend
    0.54
     spent
    0.52
     testified
    0.50
     fell
    0.49
     Spend
    0.48
     lost
    0.47
     volunteered
    0.46
    died
    0.45
    ন্
    0.45
    Activations Density 1.976%

    No Known Activations