© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7655
    Prev
    Next
    INDEX
    Explanations

    the word "milk" and words related to business issues

    oai_token-act-pair · gemini-2.0-flash

    milk

    np_max-act · gemini-2.0-flash

    milk

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     AssemblyCompany
    -0.85
    Tikang
    -0.84
    getDescriptor
    -0.84
     ComVisible
    -0.82
    uxxxx
    -0.81
    Према
    -0.79
    ///</
    -0.78
    inaison
    -0.78
    \}_{
    -0.75
    ніципа
    -0.75
    POSITIVE LOGITS
     propOrder
    0.71
     Phry
    0.59
     orale
    0.58
     Sarac
    0.54
    ,
    0.51
    (
    0.50
     acorns
    0.50
     сила
    0.50
     and
    0.50
     Dax
    0.49
    Activations Density 2.330%

    No Known Activations