© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2946
    Prev
    Next
    INDEX
    Explanations

    words related to the location of trails, roads, rivers, and banks, often including cardinal directions.

    oai_token-act-pair · gemini-2.0-flash

    bank

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     '\\;'
    -1.09
     AssemblyProduct
    -0.83
    principalColumn
    -0.77
    Datuak
    -0.76
    帖最后由
    -0.75
    SBATCH
    -0.73
     nahilalakip
    -0.72
    uxxxx
    -0.69
     springfox
    -0.69
    تقاوى
    -0.69
    POSITIVE LOGITS
     bank
    1.55
     banks
    1.35
    bank
    1.29
     Bank
    1.25
    Bank
    1.22
    banks
    1.14
     BANK
    1.11
    BANK
    1.07
    Banks
    0.93
    banking
    0.87
    Activations Density 3.064%

    No Known Activations