© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 9553
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to crime and legal wrongdoing

    oai_token-act-pair · gemini-2.0-flash

    fraud

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     fraud
    -1.25
     theft
    -1.22
     Theft
    -1.11
     Fraud
    -1.10
     stolen
    -1.10
     robbery
    -1.08
     murder
    -1.02
     thefts
    -1.00
    Fraud
    -0.98
    Theft
    -0.97
    POSITIVE LOGITS
    ArrowToggle
    0.74
    出版年
    0.66
    Datuak
    0.66
     PVA
    0.65
     ModelExpression
    0.64
    hibitions
    0.62
    exitRule
    0.61
    ​—
    0.61
     Fasc
    0.60
     jScrollPane
    0.60
    Activations Density 10.026%

    No Known Activations