© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6803
    Prev
    Next
    INDEX
    Explanations

    discussions about crime, law, and societal control using data and prediction.

    oai_token-act-pair · gemini-2.0-flash

    crime-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     crime
    -2.20
     Crime
    -2.13
     criminal
    -2.11
    Crime
    -2.02
     Criminal
    -1.95
    crime
    -1.91
    Criminal
    -1.87
     CRIME
    -1.86
    criminal
    -1.80
     CRIMINAL
    -1.77
    POSITIVE LOGITS
     OnInit
    0.54
    WaitGroup
    0.51
     réessayer
    0.51
    ษัท
    0.49
     organized
    0.47
    licó
    0.47
     libéral
    0.45
    SafeAreaView
    0.44
    וב
    0.44
     organisée
    0.44
    Activations Density 3.444%

    No Known Activations