© 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. 7367
    Prev
    Next
    INDEX
    Explanations

    contexts related to murder, attempted murder, and those ordered to be killed

    oai_token-act-pair · gemini-2.0-flash

    killing

    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
    SequentialGroup
    -0.77
     initComponents
    -0.76
     StatefulWidget
    -0.72
    IContainer
    -0.70
    UnsafeEnabled
    -0.68
     Pene
    -0.68
     typelib
    -0.67
    BeginContext
    -0.66
    AddTagHelper
    -0.66
    tagHelperRunner
    -0.66
    POSITIVE LOGITS
     killing
    1.28
     kill
    1.24
     murder
    1.22
    kill
    1.13
     kills
    1.13
     killed
    1.09
     killings
    1.02
     KILL
    1.02
     Killing
    1.02
     Kill
    1.01
    Activations Density 1.308%

    No Known Activations