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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16346
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and measurements related to bioavailability of tea

    oai_token-act-pair · gemini-2.0-flash

    Scientific documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     glass
    -0.45
     cement
    -0.44
     Glass
    -0.44
     Trow
    -0.43
     stucco
    -0.43
    Nich
    -0.42
    glass
    -0.41
     stone
    -0.41
     CASA
    -0.40
     pref
    -0.40
    POSITIVE LOGITS
     للاسماء
    0.81
     فريبيس
    0.76
    Personensuche
    0.74
    الدراسه
    0.70
    PerformLayout
    0.68
    AndEndTag
    0.66
     незавершена
    0.65
    __))
    0.65
     Dernière
    0.65
    EDEFAULT
    0.65
    Activations Density 1.661%

    No Known Activations