Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7011
    Prev
    Next
    INDEX
    Explanations

    terms related to complex physics, chemistry, and biology experiments

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     nephe
    -1.82
     flocc
    -1.82
     tetrach
    -1.81
     desorption
    -1.81
     plagioclase
    -1.81
     Efq
    -1.78
     Cæsar
    -1.76
     Jefus
    -1.74
     houſe
    -1.74
     fluence
    -1.73
    POSITIVE LOGITS
     $\
    1.13
     $
    1.03
     par
    1.02
     di
    1.00
     per
    0.97
     non
    0.91
     is
    0.90
     la
    0.88
     in
    0.88
     "
    0.88
    Activations Density 6.920%

    No Known Activations