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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 2295
    Prev
    Next
    INDEX
    Explanations

    labels, numbers, and symbols in scientific or technical writing

    oai_token-act-pair · gemini-2.0-flash

    scientific paper sections

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NLR
    -0.56
     Epist
    -0.54
     Sph
    -0.53
     CRF
    -0.51
    ibat
    -0.50
    obic
    -0.50
     MOP
    -0.50
    ganu
    -0.49
     Ters
    -0.49
     MCS
    -0.48
    POSITIVE LOGITS
     note
    0.54
     it
    0.53
     agency
    0.52
     team
    0.52
     ModelExpression
    0.51
     thing
    0.51
     scene
    0.50
     card
    0.50
     section
    0.50
     school
    0.50
    Activations Density 8.301%

    No Known Activations