© 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. 7783
    Prev
    Next
    INDEX
    Explanations

    words associated with crimes, especially violent crimes like murder.

    oai_token-act-pair · gemini-2.0-flash

    murders

    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
    kuuta
    -0.81
    IntoConstraints
    -0.77
     oprot
    -0.69
    AccessorTable
    -0.64
     Theſe
    -0.60
    DispatchToProps
    -0.60
    DataItem
    -0.59
     Monfieur
    -0.59
    TAWA
    -0.59
     stiefel
    -0.58
    POSITIVE LOGITS
    elemField
    0.55
     betweenstory
    0.53
    PageModule
    0.50
    Архівовано
    0.45
    عر
    0.45
    ituation
    0.45
     hã
    0.44
     saldır
    0.44
    handelt
    0.44
     напа
    0.44
    Activations Density 1.487%

    No Known Activations