© 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. 6416
    Prev
    Next
    INDEX
    Explanations

    the word "counter" with various suffixes, and words associated with law enforcement

    oai_token-act-pair · gemini-2.0-flash

    counter

    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
     counter
    -3.39
     Counter
    -3.09
    counter
    -2.95
     COUNTER
    -2.83
    Counter
    -2.80
     counters
    -2.61
    COUNTER
    -2.36
     Counters
    -2.27
    counters
    -1.86
    Counters
    -1.85
    POSITIVE LOGITS
    enerys
    0.47
    fycat
    0.47
    原始内容存档于
    0.47
     savon
    0.45
     aDecoder
    0.45
    viens
    0.45
    getBean
    0.45
     counts
    0.44
     suốt
    0.43
     imageNamed
    0.43
    Activations Density 3.544%

    No Known Activations