© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6191
    Prev
    Next
    INDEX
    Explanations

    reports of violence.

    oai_token-act-pair · gemini-2.0-flash

    criminals

    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
     vœux
    -0.56
     AssemblyCulture
    -0.53
     viewDidLoad
    -0.53
     layui
    -0.52
    BindView
    -0.52
     femininas
    -0.51
     démocr
    -0.49
     educativas
    -0.49
    providedIn
    -0.48
     Allociné
    -0.48
    POSITIVE LOGITS
     thieves
    0.90
     thugs
    0.89
     hackers
    0.81
     robbers
    0.76
     bandits
    0.73
     terrorists
    0.73
     criminals
    0.71
     gunmen
    0.71
     mobs
    0.71
     unscrupulous
    0.71
    Activations Density 2.689%

    No Known Activations