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. 9876
    Prev
    Next
    INDEX
    Explanations

    commonly used words like 'the', 'a', 'of', 'to', or short numbers near other frequent words

    oai_token-act-pair · gemini-2.0-flash

    the

    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
    ologically
    -0.51
    DispatchToProps
    -0.49
    matically
    -0.45
    mapStateToProps
    -0.44
    alians
    -0.44
    ology
    -0.44
    ures
    -0.44
    culi
    -0.44
    otypic
    -0.43
    iest
    -0.43
    POSITIVE LOGITS
     religieuses
    0.74
     quelcon
    0.72
     specchio
    0.71
     chré
    0.69
     définiti
    0.68
    HtmlAttribute
    0.66
     scolaires
    0.66
     stället
    0.66
     européennes
    0.65
     varandra
    0.64
    Activations Density 4.051%

    No Known Activations