© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14387
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to violent crime, especially murder.

    oai_token-act-pair · gemini-2.0-flash

    actions and events in a narrative context

    np_token-act-pair-logits · gpt-4o-mini

    crime descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     архивлан
    -0.65
     '\\;'
    -0.59
    EndInit
    -0.59
     HasFactory
    -0.59
    roux
    -0.56
    BeginInit
    -0.54
    UpInside
    -0.52
     '.';
    -0.50
     дописавши
    -0.48
    mapStateToProps
    -0.48
    POSITIVE LOGITS
     kasarigan
    0.71
    ImageContext
    0.59
     climbed
    0.58
     TextAppearance
    0.57
     opened
    0.56
     kicked
    0.55
     pulled
    0.55
     clearfix
    0.54
    
    0.53
     Clerks
    0.51
    Activations Density 2.285%

    No Known Activations