© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1034
    Prev
    Next
    INDEX
    Explanations

    words and phrases used in crime reports that are also related to political science

    oai_token-act-pair · gemini-2.0-flash

    victim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     victim
    -1.84
     victims
    -1.71
    victim
    -1.56
     Victims
    -1.54
     Victim
    -1.47
    Victim
    -1.42
     víctima
    -1.31
     victime
    -1.18
     víctimas
    -1.17
     VICT
    -1.16
    POSITIVE LOGITS
    UBL
    0.54
    Seeder
    0.53
    друг
    0.53
     sanitaires
    0.52
     quoi
    0.51
     매우
    0.51
    россий
    0.50
     peinture
    0.50
     industriels
    0.50
    Inverse
    0.50
    Activations Density 12.660%

    No Known Activations