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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 9410
    Prev
    Next
    INDEX
    Explanations

    mathematical or statistical formulas and numbers, often in scientific contexts

    oai_token-act-pair · gemini-2.0-flash

    numbers written as words

    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
     newOwner
    -0.49
    OGND
    -0.44
    avadoc
    -0.44
    DockStyle
    -0.44
    !")
    
    -0.43
    posium
    -0.43
     Efq
    -0.41
     raccoon
    -0.41
     Arco
    -0.41
    bibinfo
    -0.41
    POSITIVE LOGITS
     Five
    0.89
     Seven
    0.83
    Five
    0.83
     Six
    0.80
     seven
    0.79
    Seven
    0.79
     sixth
    0.78
     five
    0.77
     seventh
    0.77
    AddTagHelper
    0.76
    Activations Density 23.626%

    No Known Activations