© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11996
    Prev
    Next
    INDEX
    Explanations

    titles of people, affiliations, organizations, governmental bodies, places, and educational degree titles, especially in the "category" sections.

    oai_token-act-pair · gemini-2.0-flash

    Academic fields/research

    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
    ReusableCell
    -0.82
     nakalista
    -0.64
     ujednoznacz
    -0.56
    LElement
    -0.56
    PMailer
    -0.55
    Ingredients
    -0.54
    INGREDIENTS
    -0.53
    Personendaten
    -0.52
    </tfoot>
    -0.52
    
    -0.51
    POSITIVE LOGITS
    titleMargin
    0.50
     Strongly
    0.50
     Expenditures
    0.49
     remarqu
    0.49
     Reforms
    0.49
     Renewed
    0.49
     attirer
    0.48
     Expenditure
    0.48
     doInBackground
    0.48
     AssemblyTitle
    0.47
    Activations Density 11.546%

    No Known Activations